feat(prd): add missing steps 2b (vision) and 2c (executive summary)#1675
Merged
bmadcode merged 1 commit intobmad-code-org:mainfrom Feb 16, 2026
Merged
feat(prd): add missing steps 2b (vision) and 2c (executive summary)#1675bmadcode merged 1 commit intobmad-code-org:mainfrom
bmadcode merged 1 commit intobmad-code-org:mainfrom
Conversation
The PRD workflow step-02 was refactored to be discovery-only with forward references to steps 2b and 2c, but those files were never created. This left a gap where the workflow jumped from classification directly to success criteria with no executive summary generation. - Add step-02b-vision.md: collaborative vision/differentiator discovery - Add step-02c-executive-summary.md: generate and append exec summary - Update step-02 nextStepFile to chain through 02b instead of skipping to 03
🤖 Augment PR SummarySummary: This PR fills a workflow gap in PRD creation by adding the missing “vision” and “executive summary” steps between discovery/classification and success criteria. Changes:
Technical Notes: The new steps follow the existing A/P/C menu pattern and update 🤖 Was this summary useful? React with 👍 or 👎 |
![augmentcode[bot]](https://avatars.githubusercontent.com/in/1027498?s=60&v=4){kind=small}
|
|
||
| # Step 2b: Product Vision Discovery | ||
|
|
||
| **Progress: Step 2b of 13** - Next: Executive Summary |
There was a problem hiding this comment.
The Progress: Step 2b of 13 counter appears inconsistent with other create-prd steps (several still show totals of 11 or 12), which may confuse users about where they are in the workflow; consider aligning the total-step numbers across the whole chain.
Severity: low
Other Locations
src/bmm/workflows/2-plan-workflows/create-prd/steps-c/step-02c-executive-summary.md:16src/bmm/workflows/2-plan-workflows/create-prd/steps-c/step-01-init.md:16src/bmm/workflows/2-plan-workflows/create-prd/steps-c/step-03-success.md:16src/bmm/workflows/2-plan-workflows/create-prd/steps-c/step-04-journeys.md:16src/bmm/workflows/2-plan-workflows/create-prd/steps-c/step-07-project-type.md:19src/bmm/workflows/2-plan-workflows/create-prd/steps-c/step-11-polish.md:17
🤖 Was this useful? React with 👍 or 👎, or 🚀 if it prevented an incident/outage.
📝 WalkthroughWalkthroughThe pull request introduces two new workflow step files (Vision Discovery and Executive Summary Generation) for the product planning workflow and updates the Discovery step's navigation to route through the new Vision step before proceeding to the Executive Summary step. Changes
Estimated code review effort🎯 3 (Moderate) | ⏱️ ~25 minutes Possibly related issues
Possibly related PRs
Suggested reviewers
🚥 Pre-merge checks | ✅ 4✅ Passed checks (4 passed)
✏️ Tip: You can configure your own custom pre-merge checks in the settings. ✨ Finishing touches🧪 Generate unit tests (beta)
Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. Comment |
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
There was a problem hiding this comment.
Actionable comments posted: 8
Caution
Some comments are outside the diff and can’t be posted inline due to platform limitations.
⚠️ Outside diff range comments (3)
src/bmm/workflows/2-plan-workflows/create-prd/steps-c/step-02-discovery.md (3)
48-115:⚠️ Potential issue | 🟠 MajorImpossible ordering: requires detected values before discovery.
You instruct “LOAD classification data BEFORE starting discovery conversation,” but the lookup keys are
{{detectedProjectType}}and{{detectedDomain}}, which are only known after discovery. This sequence is logically impossible and will stall or generate nonsense lookups.Suggested fix
- - 🎯 LOAD classification data BEFORE starting discovery conversation + - 🎯 Begin discovery conversation, identify detected project type/domain, then load classification data
99-167:⚠️ Potential issue | 🟠 MajorPlaceholder name mismatches will leak templates or lose data.
You use
{{detectedProjectType}},{{detectedType}},{{projectType}}, and{{domain}}interchangeably. This inconsistency will result in empty values or wrong mappings when saving to frontmatter and showing summaries. Normalize to one set of variable names across lookup, summary, and frontmatter save.Example normalization (pick one naming scheme)
- - Find row where project_type matches {{detectedProjectType}} + - Find row where project_type matches {{detectedType}} - projectType: {{projectType}} + projectType: {{detectedType}}
78-93:⚠️ Potential issue | 🟠 MajorNo fallback if
documentCountsis missing.The step assumes
documentCountsexists in frontmatter and instructs announcing counts. If the key is missing (common in partial runs), the agent will emit raw placeholders or crash downstream logic. Add a fallback (“unknown” or 0) and a recovery prompt.Suggested fallback
- Read the frontmatter from `{outputFile}` to get document counts: + Read the frontmatter from `{outputFile}` to get document counts; if missing, treat all counts as 0 and state that no counts were provided.
🤖 Fix all issues with AI agents
In `@src/bmm/workflows/2-plan-workflows/create-prd/steps-c/step-02b-vision.md`:
- Around line 56-61: The step-02b-vision.md text contradicts itself by saying
“does NOT write to the document” while later requiring a frontmatter update;
update the wording to explicitly allow frontmatter mutations but forbid any
body/content writes: change the sentence in step-02b-vision.md to state that
this step performs discovery only and must not append or modify body content,
but may update frontmatter fields (only for the C frontmatter/phase), and add a
short note that frontmatter updates are restricted to C to prevent agents from
editing document body.
- Line 49: The phrase "🎯 Show your analysis before taking any action" exposes
internal reasoning and conflicts with the facilitator-only posture; replace that
exact string with a brief, user-facing instruction such as "🎯 Provide a short
recap or plan of next steps" (or similar) so the step communicates a high-level
plan to the user rather than requesting internal analysis; update the content in
step-02b-vision.md where that line occurs to reflect the new wording.
- Around line 49-53: The frontmatter update (adding this step to stepsCompleted)
is currently performed unconditionally in the vision discovery flow; change the
logic so the frontmatter mutation that appends this step to stepsCompleted only
occurs when the user explicitly selects the "C" (Confirm/Continue) option from
the A/P/C menu after vision discovery. Locate the code or markdown action that
updates frontmatter/stepsCompleted in the create-prd vision step (references:
"stepsCompleted", "frontmatter", and the A/P/C menu / "C" choice) and wrap or
gate that update behind the branch or callback that handles the "C" selection so
the step is not marked complete on other choices.
- Around line 105-119: The menu currently allows selecting C (Continue to
Executive Summary) without an explicit confirmation of the "Validate
Understanding" summary; add a guard in the menu-handling logic so that option C
is disabled or rejected unless the user has explicitly confirmed the Validate
Understanding summary (e.g., track a boolean like hasConfirmedUnderstanding set
when the summary is accepted), update the IF C branch to check
hasConfirmedUnderstanding before updating outputFile.stepsCompleted and loading
nextStepFile, and if not confirmed prompt the user to confirm the Validate
Understanding summary (or offer A/P) and then redisplay the menu.
- Around line 91-103: Define an explicit output contract for the
vision/differentiator summaries used by Step 2c: add required frontmatter/memory
keys (e.g. summarized_vision, summarized_differentiator, summarized_insight) in
step-02b-vision.md and enforce a validation check before allowing transition to
[C] (fail-fast with a user-facing prompt if any key is missing or empty); update
any orchestration logic that advances to "Step 2c" to read these exact keys
rather than implicit state so the handoff is deterministic.
In
`@src/bmm/workflows/2-plan-workflows/create-prd/steps-c/step-02c-executive-summary.md`:
- Around line 116-138: The append routine currently always adds the literal "##
Executive Summary" and "## Project Classification" blocks and must be changed to
first detect those headings (search for the "## Executive Summary" and "##
Project Classification" headings) and if present replace the existing section
content with the new {vision_alignment_content},
{product_differentiator_content}, and {project_classification_content}
respectively; if a heading is not found, append the block as before. Implement
this guard by locating and replacing the text between the "## Executive Summary"
heading and the next same-or-higher-level heading, and likewise replace the "##
Project Classification" section, using robust regex or markdown-parsing
utilities to avoid duplicate sections on reruns.
- Around line 24-44: Update the conflicting instruction in the Universal Rules
that reads "YOU ARE A FACILITATOR, not a content generator" so it explicitly
allows content drafting when a step requires it: change the line to something
like "YOU ARE A FACILITATOR: collaborate and draft content with the user; do not
append final content without explicit user approval." Ensure this reconciles
with Step-Specific Rules in step-02c-executive-summary.md (the "🎯 Generate
Executive Summary" and "🚫 FORBIDDEN to append content without user approval via
'C'") so the agent knows it may generate draft content but must present it for
review before saving or appending.
- Around line 54-74: Add a preflight validation before generating the executive
summary that checks for required prerequisite insights (classification from step
2 and vision/differentiator from step 2b) referenced in the "Synthesize
Available Context" / "EXECUTIVE SUMMARY GENERATION SEQUENCE" sections; if any
required item is missing or empty, stop the draft flow and prompt the user to
provide or confirm the missing data (mention which specific item is missing) and
offer to pull in available inputs from steps 1/2/2b or to run the prior step(s)
again before proceeding.
|
|
||
| ## EXECUTION PROTOCOLS: | ||
|
|
||
| - 🎯 Show your analysis before taking any action |
There was a problem hiding this comment.
“Show your analysis” conflicts with facilitation-only posture.
This instruction can force exposure of internal reasoning, which undermines the facilitator-only guidance and risks leaking internal logic. Replace with a short, user-facing recap or plan instead of “analysis.”
Suggested fix
- - 🎯 Show your analysis before taking any action
+ - 🎯 Provide a brief, user-facing recap before taking any action📝 Committable suggestion
‼️ IMPORTANT
Carefully review the code before committing. Ensure that it accurately replaces the highlighted code, contains no missing lines, and has no issues with indentation. Thoroughly test & benchmark the code to ensure it meets the requirements.
Suggested change
| - 🎯 Show your analysis before taking any action | |
| - 🎯 Provide a brief, user-facing recap before taking any action |
🤖 Prompt for AI Agents
In `@src/bmm/workflows/2-plan-workflows/create-prd/steps-c/step-02b-vision.md` at
line 49, The phrase "🎯 Show your analysis before taking any action" exposes
internal reasoning and conflicts with the facilitator-only posture; replace that
exact string with a brief, user-facing instruction such as "🎯 Provide a short
recap or plan of next steps" (or similar) so the step communicates a high-level
plan to the user rather than requesting internal analysis; update the content in
step-02b-vision.md where that line occurs to reflect the new wording.
Comment on lines
+49
to
+53
| - 🎯 Show your analysis before taking any action | ||
| - ⚠️ Present A/P/C menu after vision discovery is complete | ||
| - 📖 Update frontmatter, adding this step to the end of the list of stepsCompleted | ||
| - 🚫 FORBIDDEN to load next step until C is selected | ||
|
|
There was a problem hiding this comment.
Gate frontmatter updates to explicit user confirmation.
Line 51 instructs updating frontmatter as part of execution protocols without tying it to the [C] confirmation. That can mark the step complete even if the user never approves moving forward. Make this update conditional on C only.
Suggested fix
- - 📖 Update frontmatter, adding this step to the end of the list of stepsCompleted
+ - 📖 ONLY when user selects 'C', update frontmatter by adding this step to the end of stepsCompleted🤖 Prompt for AI Agents
In `@src/bmm/workflows/2-plan-workflows/create-prd/steps-c/step-02b-vision.md`
around lines 49 - 53, The frontmatter update (adding this step to
stepsCompleted) is currently performed unconditionally in the vision discovery
flow; change the logic so the frontmatter mutation that appends this step to
stepsCompleted only occurs when the user explicitly selects the "C"
(Confirm/Continue) option from the A/P/C menu after vision discovery. Locate the
code or markdown action that updates frontmatter/stepsCompleted in the
create-prd vision step (references: "stepsCompleted", "frontmatter", and the
A/P/C menu / "C" choice) and wrap or gate that update behind the branch or
callback that handles the "C" selection so the step is not marked complete on
other choices.
Comment on lines
+56
to
+61
| - Current document and frontmatter from steps 1 and 2 are available | ||
| - Project classification exists from step 2 (project type, domain, complexity, context) | ||
| - Input documents already loaded are in memory (product briefs, research, brainstorming, project docs) | ||
| - No executive summary content yet (that's step 2c) | ||
| - This step ONLY discovers — it does NOT write to the document | ||
|
|
There was a problem hiding this comment.
Contradiction: “no document writes” vs required frontmatter update.
You explicitly state “does NOT write to the document,” but later require updating frontmatter, which is part of the document. This ambiguity will cause inconsistent agent behavior. Clarify that body content must not be appended, while frontmatter updates are allowed only on C.
Suggested fix
- - This step ONLY discovers — it does NOT write to the document
+ - This step ONLY discovers — it does NOT append to the document body (frontmatter update only on C)🤖 Prompt for AI Agents
In `@src/bmm/workflows/2-plan-workflows/create-prd/steps-c/step-02b-vision.md`
around lines 56 - 61, The step-02b-vision.md text contradicts itself by saying
“does NOT write to the document” while later requiring a frontmatter update;
update the wording to explicitly allow frontmatter mutations but forbid any
body/content writes: change the sentence in step-02b-vision.md to state that
this step performs discovery only and must not append or modify body content,
but may update frontmatter fields (only for the C frontmatter/phase), and add a
short note that frontmatter updates are restricted to C to prevent agents from
editing document body.
Comment on lines
+91
to
+103
| ### 4. Validate Understanding | ||
|
|
||
| Reflect back what you've heard and confirm: | ||
|
|
||
| "Here's what I'm hearing about your vision and differentiator: | ||
|
|
||
| **Vision:** {{summarized_vision}} | ||
| **What Makes It Special:** {{summarized_differentiator}} | ||
| **Core Insight:** {{summarized_insight}} | ||
|
|
||
| Does this capture it? Anything I'm missing?" | ||
|
|
||
| Let the user confirm or refine your understanding. |
There was a problem hiding this comment.
No explicit output contract for vision/differentiator summaries.
Step 2c depends on “vision and differentiator insights,” but this step never defines where those summaries live (frontmatter keys, memory variables, etc.). That’s a broken handoff. Define concrete fields and require them to be set before allowing [C].
Example contract addition
+ - On confirmation, store:
+ visionDiscovery:
+ visionSummary: {{summarized_vision}}
+ differentiatorSummary: {{summarized_differentiator}}
+ coreInsight: {{summarized_insight}}🤖 Prompt for AI Agents
In `@src/bmm/workflows/2-plan-workflows/create-prd/steps-c/step-02b-vision.md`
around lines 91 - 103, Define an explicit output contract for the
vision/differentiator summaries used by Step 2c: add required frontmatter/memory
keys (e.g. summarized_vision, summarized_differentiator, summarized_insight) in
step-02b-vision.md and enforce a validation check before allowing transition to
[C] (fail-fast with a user-facing prompt if any key is missing or empty); update
any orchestration logic that advances to "Step 2c" to read these exact keys
rather than implicit state so the handoff is deterministic.
Comment on lines
+105
to
+119
| ### N. Present MENU OPTIONS | ||
|
|
||
| Present your understanding of the product vision for review, then display menu: | ||
|
|
||
| "Based on our conversation, I have a clear picture of your product vision and what makes it special. I'll use these insights to draft the Executive Summary in the next step. | ||
|
|
||
| **What would you like to do?**" | ||
|
|
||
| Display: "**Select:** [A] Advanced Elicitation [P] Party Mode [C] Continue to Executive Summary (Step 2c of 13)" | ||
|
|
||
| #### Menu Handling Logic: | ||
| - IF A: Read fully and follow: {advancedElicitationTask} with the current vision insights, process the enhanced insights that come back, ask user if they accept the improvements, if yes update understanding then redisplay menu, if no keep original understanding then redisplay menu | ||
| - IF P: Read fully and follow: {partyModeWorkflow} with the current vision insights, process the collaborative insights, ask user if they accept the changes, if yes update understanding then redisplay menu, if no keep original understanding then redisplay menu | ||
| - IF C: Update {outputFile} frontmatter by adding this step name to the end of stepsCompleted array, then read fully and follow: {nextStepFile} | ||
| - IF Any other: help user respond, then redisplay menu |
There was a problem hiding this comment.
Menu allows [C] without confirmed understanding.
There’s no explicit guard that the user has confirmed the “Validate Understanding” summary before proceeding. A user can select C immediately after a partial conversation. Require explicit confirmation before enabling C.
Suggested guard
- - IF C: Update {outputFile} frontmatter ...
+ - IF C: ONLY if user has confirmed the vision/differentiator summary; then update {outputFile} frontmatter ...🤖 Prompt for AI Agents
In `@src/bmm/workflows/2-plan-workflows/create-prd/steps-c/step-02b-vision.md`
around lines 105 - 119, The menu currently allows selecting C (Continue to
Executive Summary) without an explicit confirmation of the "Validate
Understanding" summary; add a guard in the menu-handling logic so that option C
is disabled or rejected unless the user has explicitly confirmed the Validate
Understanding summary (e.g., track a boolean like hasConfirmedUnderstanding set
when the summary is accepted), update the IF C branch to check
hasConfirmedUnderstanding before updating outputFile.stepsCompleted and loading
nextStepFile, and if not confirmed prompt the user to confirm the Validate
Understanding summary (or offer A/P) and then redisplay the menu.
Comment on lines
+24
to
+44
| ### Universal Rules: | ||
|
|
||
| - 🛑 NEVER generate content without user input | ||
| - 📖 CRITICAL: Read the complete step file before taking any action | ||
| - 🔄 CRITICAL: When loading next step with 'C', ensure the entire file is read | ||
| - ✅ ALWAYS treat this as collaborative discovery between PM peers | ||
| - 📋 YOU ARE A FACILITATOR, not a content generator | ||
| - ✅ YOU MUST ALWAYS SPEAK OUTPUT In your Agent communication style with the config `{communication_language}` | ||
|
|
||
| ### Role Reinforcement: | ||
|
|
||
| - ✅ You are a product-focused PM facilitator collaborating with an expert peer | ||
| - ✅ We engage in collaborative dialogue, not command-response | ||
| - ✅ Content is drafted collaboratively — present for review before saving | ||
|
|
||
| ### Step-Specific Rules: | ||
|
|
||
| - 🎯 Generate Executive Summary content based on discovered insights | ||
| - 💬 Present draft content for user review and refinement before appending | ||
| - 🚫 FORBIDDEN to append content without user approval via 'C' | ||
| - 🎯 Content must be dense, precise, and zero-fluff (PRD quality standards) |
There was a problem hiding this comment.
Contradiction: “not a content generator” vs required content generation.
Universal rules state you’re “not a content generator,” but Step 2c’s primary purpose is to generate Executive Summary content. This conflict will cause inconsistent agent behavior. Align the universal rule with step-specific requirements.
Suggested fix
- - 📋 YOU ARE A FACILITATOR, not a content generator
+ - 📋 YOU ARE A FACILITATOR who drafts content collaboratively for review📝 Committable suggestion
‼️ IMPORTANT
Carefully review the code before committing. Ensure that it accurately replaces the highlighted code, contains no missing lines, and has no issues with indentation. Thoroughly test & benchmark the code to ensure it meets the requirements.
Suggested change
| ### Universal Rules: | |
| - 🛑 NEVER generate content without user input | |
| - 📖 CRITICAL: Read the complete step file before taking any action | |
| - 🔄 CRITICAL: When loading next step with 'C', ensure the entire file is read | |
| - ✅ ALWAYS treat this as collaborative discovery between PM peers | |
| - 📋 YOU ARE A FACILITATOR, not a content generator | |
| - ✅ YOU MUST ALWAYS SPEAK OUTPUT In your Agent communication style with the config `{communication_language}` | |
| ### Role Reinforcement: | |
| - ✅ You are a product-focused PM facilitator collaborating with an expert peer | |
| - ✅ We engage in collaborative dialogue, not command-response | |
| - ✅ Content is drafted collaboratively — present for review before saving | |
| ### Step-Specific Rules: | |
| - 🎯 Generate Executive Summary content based on discovered insights | |
| - 💬 Present draft content for user review and refinement before appending | |
| - 🚫 FORBIDDEN to append content without user approval via 'C' | |
| - 🎯 Content must be dense, precise, and zero-fluff (PRD quality standards) | |
| ### Universal Rules: | |
| - 🛑 NEVER generate content without user input | |
| - 📖 CRITICAL: Read the complete step file before taking any action | |
| - 🔄 CRITICAL: When loading next step with 'C', ensure the entire file is read | |
| - ✅ ALWAYS treat this as collaborative discovery between PM peers | |
| - 📋 YOU ARE A FACILITATOR who drafts content collaboratively for review | |
| - ✅ YOU MUST ALWAYS SPEAK OUTPUT In your Agent communication style with the config `{communication_language}` | |
| ### Role Reinforcement: | |
| - ✅ You are a product-focused PM facilitator collaborating with an expert peer | |
| - ✅ We engage in collaborative dialogue, not command-response | |
| - ✅ Content is drafted collaboratively — present for review before saving | |
| ### Step-Specific Rules: | |
| - 🎯 Generate Executive Summary content based on discovered insights | |
| - 💬 Present draft content for user review and refinement before appending | |
| - 🚫 FORBIDDEN to append content without user approval via 'C' | |
| - 🎯 Content must be dense, precise, and zero-fluff (PRD quality standards) |
🤖 Prompt for AI Agents
In
`@src/bmm/workflows/2-plan-workflows/create-prd/steps-c/step-02c-executive-summary.md`
around lines 24 - 44, Update the conflicting instruction in the Universal Rules
that reads "YOU ARE A FACILITATOR, not a content generator" so it explicitly
allows content drafting when a step requires it: change the line to something
like "YOU ARE A FACILITATOR: collaborate and draft content with the user; do not
append final content without explicit user approval." Ensure this reconciles
with Step-Specific Rules in step-02c-executive-summary.md (the "🎯 Generate
Executive Summary" and "🚫 FORBIDDEN to append content without user approval via
'C'") so the agent knows it may generate draft content but must present it for
review before saving or appending.
Comment on lines
+54
to
+74
| ## CONTEXT BOUNDARIES: | ||
|
|
||
| - Current document and frontmatter from steps 1, 2, and 2b are available | ||
| - Project classification exists from step 2 (project type, domain, complexity, context) | ||
| - Vision and differentiator insights exist from step 2b | ||
| - Input documents from step 1 are available (product briefs, research, brainstorming, project docs) | ||
| - This step generates and appends the first substantive content to the PRD | ||
|
|
||
| ## YOUR TASK: | ||
|
|
||
| Draft the Executive Summary section using all discovered insights, present it for user review, and append it to the PRD document when approved. | ||
|
|
||
| ## EXECUTIVE SUMMARY GENERATION SEQUENCE: | ||
|
|
||
| ### 1. Synthesize Available Context | ||
|
|
||
| Review all available context before drafting: | ||
| - Classification from step 2: project type, domain, complexity, project context | ||
| - Vision and differentiator from step 2b: what makes this special, core insight | ||
| - Input documents: product briefs, research, brainstorming, project docs | ||
|
|
There was a problem hiding this comment.
Missing validation that prerequisite insights exist.
You assume classification and vision/differentiator insights exist, but there is no guard if step 2b didn’t capture them or if the run is partial. Add a preflight check and prompt the user to fill gaps before drafting.
Suggested preflight gate
+ - If classification or vision/differentiator summaries are missing, ask targeted questions to fill them before drafting.🤖 Prompt for AI Agents
In
`@src/bmm/workflows/2-plan-workflows/create-prd/steps-c/step-02c-executive-summary.md`
around lines 54 - 74, Add a preflight validation before generating the executive
summary that checks for required prerequisite insights (classification from step
2 and vision/differentiator from step 2b) referenced in the "Synthesize
Available Context" / "EXECUTIVE SUMMARY GENERATION SEQUENCE" sections; if any
required item is missing or empty, stop the draft flow and prompt the user to
provide or confirm the missing data (mention which specific item is missing) and
offer to pull in available inputs from steps 1/2/2b or to run the prior step(s)
again before proceeding.
Comment on lines
+116
to
+138
| ## APPEND TO DOCUMENT: | ||
|
|
||
| When user selects 'C', append the following content structure directly to the document: | ||
|
|
||
| ```markdown | ||
| ## Executive Summary | ||
|
|
||
| {vision_alignment_content} | ||
|
|
||
| ### What Makes This Special | ||
|
|
||
| {product_differentiator_content} | ||
|
|
||
| ## Project Classification | ||
|
|
||
| {project_classification_content} | ||
| ``` | ||
|
|
||
| Where: | ||
| - `{vision_alignment_content}` — Product vision, target users, and the problem being solved. Dense, precise summary drawn from step 2b vision discovery. | ||
| - `{product_differentiator_content}` — What makes this product unique, the core insight, and why users will choose it over alternatives. Drawn from step 2b differentiator discovery. | ||
| - `{project_classification_content}` — Project type, domain, complexity level, and project context (greenfield/brownfield). Drawn from step 2 classification. | ||
|
|
There was a problem hiding this comment.
Append risks duplicate sections on reruns.
The “Append to document” block always adds ## Executive Summary and ## Project Classification without checking if they already exist (e.g., re-run after edits). This can create duplicated sections and inconsistent PRDs. Add a guard to replace or update existing sections instead of blindly appending.
Suggested guard
- When user selects 'C', append the following content structure directly to the document:
+ When user selects 'C', append the following content only if these sections are not already present; otherwise, replace the existing sections.🤖 Prompt for AI Agents
In
`@src/bmm/workflows/2-plan-workflows/create-prd/steps-c/step-02c-executive-summary.md`
around lines 116 - 138, The append routine currently always adds the literal "##
Executive Summary" and "## Project Classification" blocks and must be changed to
first detect those headings (search for the "## Executive Summary" and "##
Project Classification" headings) and if present replace the existing section
content with the new {vision_alignment_content},
{product_differentiator_content}, and {project_classification_content}
respectively; if a heading is not found, append the block as before. Implement
this guard by locating and replacing the text between the "## Executive Summary"
heading and the next same-or-higher-level heading, and likewise replace the "##
Project Classification" section, using robust regex or markdown-parsing
utilities to avoid duplicate sections on reruns.
Contributor
|
@coderabbitai review |
This was referenced Feb 17, 2026
This was referenced Mar 7, 2026
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
nextStepFileto chain throughstep-02binstead of skipping directly tostep-03This closes the gap left when step-02 was refactored to be discovery-only with forward references to steps 2b and 2c that were never created. The workflow previously jumped from classification (step 2) to success criteria (step 3), which assumed the Executive Summary already existed.
Chain:
step-02→step-02b→step-02c→step-03Test plan
nextStepFilechain: step-02 → step-02b → step-02c → step-03 → step-04