feat: Add personalized-outreach-agent template#190
Conversation
|
Warning Review limit reached
Next review available in: 37 minutes Enable usage-based reviews in Billing to review now. Otherwise, wait until the next included review is available. How can I continue?After more reviews become available, a review can be triggered using the To avoid repeated limits, reduce automatic review volume by pausing incremental auto-reviews earlier, using label-based review opt-in, excluding WIP or generated PR titles, or requesting reviews manually when the PR is ready. If your team needs uninterrupted high-volume reviews, an organization admin can enable usage-based reviews. How do review limits work?CodeRabbit enforces per-developer PR review limits for each organization. Most developers receive the normal plan review availability. For paid Pro and Pro+ PR reviews, CodeRabbit uses adaptive limits for sustained high-volume activity. When a developer's recent PR review activity reaches the 95th percentile or higher among CodeRabbit users, additional reviews become available more gradually as earlier reviews age out of the rolling window. Please refer docs for additional details. Review details⚙️ Run configurationConfiguration used: Repository UI (base), Organization UI (inherited) Review profile: ASSERTIVE Plan: Pro Run ID: 📒 Files selected for processing (2)
WalkthroughMission briefing: this dossier adds a new “Personalized Outreach Agent” kit. It defines the flow, model configs, prompts, constitution, template config, ignore rules, and documentation for a write-verify-rewrite outreach pipeline. ChangesPersonalized Outreach Agent Kit
Suggested reviewers: 🚥 Pre-merge checks | ✅ 5✅ Passed checks (5 passed)
✨ 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 |
:robot_face: AgentKit Structural ValidationNew Contributions Detected
Check Results
🎉 All checks passed! This contribution follows the AgentKit structure. |
|
Failure recorded at 2026-07-07T17:09:46Z UTC. If this PR is not fixed within 4 weeks it will be automatically closed. |
Ganesh-0509
force-pushed
the
feat/personalized-outreach-agent
branch
from
496dded to
c10f70c
Compare
A self-fact-checking outreach writer. It drafts a personalized job-outreach message from a company brief and the candidate's real profile, then a Verifier step audits every claim against that profile, removes anything unsupported, and returns a transparent verification report alongside the corrected message. Contribution type: template (single flow, 4 nodes).
Ganesh-0509
force-pushed
the
feat/personalized-outreach-agent
branch
from
c10f70c to
bc672e0
Compare
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
There was a problem hiding this comment.
Actionable comments posted: 2
🤖 Prompt for all review comments with AI agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
Inline comments:
In
`@kits/personalized-outreach-agent/prompts/personalized-outreach-agent_llmnode-613_system_0.md`:
- Around line 12-14: The verifier format in the prompt includes an extra
trailing character that should be removed so the output contract is exact and
unambiguous. Update the instructions around the claim-checking format in the
personalized-outreach-agent prompt so the final line ends cleanly with the
intended sentence, and verify the surrounding wording still clearly references
the supported/removed bullet format and the “All claims verified against the
profile — nothing removed.” fallback.
In `@kits/personalized-outreach-agent/README.md`:
- Around line 34-42: The README example uses an unlabeled fenced code block,
which triggers the markdownlint warning. Update the example fence in the
verification section to use a text label so the docs stay lint-clean. Make this
change in the markdown snippet that shows the VERIFIED MESSAGE and VERIFICATION
REPORT, keeping the content the same and only adjusting the fence label.
🪄 Autofix (Beta)
Fix all unresolved CodeRabbit comments on this PR:
- Push a commit to this branch (recommended)
- Create a new PR with the fixes
ℹ️ Review info
⚙️ Run configuration
Configuration used: Repository UI (base), Organization UI (inherited)
Review profile: ASSERTIVE
Plan: Pro
Run ID: 8dab9ad2-fcc1-4fd7-a23d-13af7e54071d
📒 Files selected for processing (12)
kits/personalized-outreach-agent/.gitignorekits/personalized-outreach-agent/README.mdkits/personalized-outreach-agent/agent.mdkits/personalized-outreach-agent/constitutions/default.mdkits/personalized-outreach-agent/flows/personalized-outreach-agent.tskits/personalized-outreach-agent/lamatic.config.tskits/personalized-outreach-agent/model-configs/personalized-outreach-agent_llmnode-119_generative-model-name.tskits/personalized-outreach-agent/model-configs/personalized-outreach-agent_llmnode-613_generative-model-name.tskits/personalized-outreach-agent/prompts/personalized-outreach-agent_llmnode-119_system_0.mdkits/personalized-outreach-agent/prompts/personalized-outreach-agent_llmnode-119_user_1.mdkits/personalized-outreach-agent/prompts/personalized-outreach-agent_llmnode-613_system_0.mdkits/personalized-outreach-agent/prompts/personalized-outreach-agent_llmnode-613_user_1.md
…label README code fence)
|
Thanks for the review! Addressed both points in
|
|
Hi @Ganesh-0509! 👋 Before this PR can be reviewed by maintainers, please resolve all comments and requested changes from the CodeRabbit automated review. Steps to follow:
This helps keep the review process efficient for everyone. Thank you! 🙏 |
1 participant
Summary
Adds Personalized Outreach Agent — a template (single flow, 4 nodes) that writes personalized job-outreach messages that never lie about the candidate.
Most LLM outreach tools happily exaggerate — inventing skills or experience the candidate doesn't have. This flow fixes that with a write → verify → rewrite loop:
It's an anti-hallucination guardrail applied to an everyday task — the "verify/optimize" side of building trustworthy agentic apps.
Contribution Type
kits/personalized-outreach-agent/)Flow (4 nodes)
API Request→LLM (Writer)→LLM (Verifier)→API ResponseInputs:
companyInfo,candidateProfile· Output: verified message + verification reportChecklist
kebab-casefolder matching the flow IDREADME.md+agent.mdlamatic.config.tswith valid metadata (type: template)Built, deployed, and tested in Lamatic Studio.
kits/personalized-outreach-agent/template for a “Personalized Outreach Agent” workflow that drafts personalized job outreach from a company brief and candidate profile, then verifies the draft against the candidate’s real experience to remove or soften unsupported claims.flows/personalized-outreach-agent.ts, defining a 4-node sequence:API Requesttrigger →LLMwriter →LLMverifier →API Response, with a response mapping back to the verifier output.lamatic.config.ts, marking the kit as atemplateand registering thepersonalized-outreach-agentstep.README.mdandagent.mdexplaining the inputs, write/verify flow, output format, usage steps, and prompt/reference conventions.constitutions/default.mdcovering safety, data handling, and tone rules for the agent.companyInfo,candidateProfile, and the draft message..gitignoreto exclude.lamatic/,node_modules/, and local env files.