# OutcomeOps: Context Engineering for AI-Assisted Development OSS GitHub Repo

> Source: <https://github.com/bcarpio/outcome-ops-ai-assist>
> Published: 2026-11-20 12:59:28+00:00

**Key takeaway:** OutcomeOps AI Assist pairs semantic vector search reranked with Cohere Rerank 3.5 against ADRs and code-maps with a DynamoDB symbol graph so structural questions like a symbol's callers and implementers are answered from the graph rather than text similarity.

**OutcomeOps AI Assist** is a generic, language- and framework-agnostic platform for
AI-powered code generation, pull-request review, and knowledge-base retrieval that deploys
entirely into your own AWS account. It grounds AI in your organization's standards — ADRs,
code-maps, and architectural decisions — so generated code and reviews match your patterns
instead of generic defaults. The platform is **open source under the [Apache License 2.0](https://github.com/bcarpio/outcome-ops-ai-assist/blob/main/LICENSE)**;
see [CONTRIBUTING.md](https://github.com/bcarpio/outcome-ops-ai-assist/blob/main/CONTRIBUTING.md) to get involved. Security reports go through
[SECURITY.md](https://github.com/bcarpio/outcome-ops-ai-assist/blob/main/SECURITY.md).

**Trademark:** "OutcomeOps" and the OutcomeOps logo are trademarks of OutcomeOps LLC.
The Apache-2.0 license grants no trademark rights, so forks and derivatives must use a
different name.

AI generates generic code. You need code that matches **YOUR** standards.

**The problem:** Engineers spend hours adapting AI-generated code to organizational patterns, standards, and architecture decisions.

**The solution:** Give AI access to your organizational knowledge—ADRs, code-maps, architectural decisions—so it generates code that already matches your patterns.

**The proof:**

- 16-hour tasks → 15 minutes
- $2-$4 per feature
- 100-200x ROI
- Production-tested at Fortune 500

This is Context Engineering. This is OutcomeOps.

[Learn more about the OutcomeOps Methodology →](https://www.outcomeops.ai)

|   **OutcomeOps Demo: Organizational Intelligence Across Your Codebase** |   **Audit. Cost. Control. Why InfoSec Picks OutcomeOps** | 

More walkthroughs on the [OutcomeOps YouTube channel](https://www.youtube.com/@OutcomeOps).

Every pull request to this repository is reviewed by OutcomeOps itself, against the repo's own ADRs:

A real review, quoted verbatim: the license check reads the repo's ADR-008 and decides a missing copyright header on a Markdown doc is a WARN, not a FAIL. [See the pull request](https://github.com/bcarpio/outcome-ops-ai-assist/pull/19).

**Current AI coding tools:**

- Generate generic implementations
- Don't know your architectural decisions
- Ignore your coding standards
- Require hours of manual adaptation
- **You still spend most of your time rewriting AI code**

**OutcomeOps is different:**

- Understands YOUR codebase patterns
- Knows YOUR architectural decisions (via ADRs)
- Generates code matching YOUR standards
- Includes tests automatically
- **AI does the work. You do the review.**

**1. Ingest Organizational Knowledge**

- ADRs (Architecture Decision Records)
- Code-maps (repo structure and patterns)
- Existing code examples
- Standards documentation

**2. Vector Search + Reranking**

- When a feature is requested (Jira story, GitHub issue)
- OutcomeOps queries your knowledge base via semantic vector search
- Reranks results using Cohere Rerank 3.5 for precision ordering
- Finds the most relevant patterns, decisions, and examples

**3. AI Generation with Context**

- Claude generates code using YOUR context
- Matches YOUR patterns, not generic templates
- Includes tests based on YOUR testing standards
- Creates MR/PR with full implementation

**4. Automated Review**

- MR analyzer checks against standards
- Validates architectural compliance
- Comments on deviations
- **Code that's 90% done when you first see it**

Vector search is good at "how do we usually do this?" It cannot reliably answer "what breaks if I change this function?", and on its own it does nothing to keep personal data out of the model's context. OutcomeOps adds two layers for that.

**A symbol graph for exact answers.** While generating code-maps, OutcomeOps extracts every definition, call, import, and interface implementation into a symbol graph stored in DynamoDB. Structural questions are answered from the graph, not from text similarity:

- `callers` ,`importers` ,`implementers` , and`definitions` of a symbol, each with file path and line
- References resolve across repositories, so a consumer in another repo, or in a workspace that was granted access, is found too ([ADR-055](https://github.com/bcarpio/outcome-ops-ai-assist/blob/main/docs/adr/ADR-055-symbol-graph-cross-module-resolution.md) ,[ADR-056](https://github.com/bcarpio/outcome-ops-ai-assist/blob/main/docs/adr/ADR-056-cross-repo-symbol-resolution.md) )
- The pull-request breaking-changes check uses it to list every consumer of a changed symbol
- Chat, code generation, and PR review query the graph alongside vector search, and the same lookups are available as MCP tools (`find_callers` ,`find_importers` ,`find_implementers` ,`find_definitions` )
- When there are no callers, the answer is an empty list, not a guess

**PII redaction at ingest.** Before a document is embedded, Amazon Comprehend `DetectPiiEntities` runs inside your AWS account and replaces names, Social Security numbers, phone numbers, account numbers, and other personal identifiers with `[REDACTED:TYPE]` placeholders. The vector store, and every chunk retrieved into a prompt, holds only the redacted text ([ADR-051](https://github.com/bcarpio/outcome-ops-ai-assist/blob/main/docs/adr/ADR-051-pii-redaction-at-ingest.md)).

- Technical identifiers developers need (URLs, IP addresses, MAC addresses, timestamps) are kept by default; the skip list is the `pii_redaction_skip_types` tfvar
- Every workspace is `STRICT` by default. An admin can set one to`NONE` (for example HR or support content where redaction defeats the purpose), and that change is written to the audit log with the old and new mode
- `pii_redaction_enabled` is the org-wide kill switch
- With `audit_stream_export_enabled` , the audit log streams through Kinesis as OCSF v1.3.0 events to your SIEM
- The raw source copy in your S3 bucket is deliberately left unredacted, so `read_source` and code generation work from the real code

**Prerequisites:**

- GitHub repo with some code
- AWS account (for Lambda deployment)
- ADRs or architectural docs (or we'll help you create them)
- AWS CLI v2, Terraform 1.5+, and Docker installed
- See [Getting Started](https://github.com/bcarpio/outcome-ops-ai-assist/blob/main/docs/getting-started.md) for the full prerequisite
list (VPC, domain/cert, Azure AD)

**Ready to get started?**

OutcomeOps is open source under the [Apache License 2.0](https://github.com/bcarpio/outcome-ops-ai-assist/blob/main/LICENSE). Clone the repo and deploy it into your own AWS account, no license or sign-up required.

A first deployment takes roughly 30 to 45 minutes (most of it building the Lambda layers and container images, see [Getting Started](https://github.com/bcarpio/outcome-ops-ai-assist/blob/main/docs/getting-started.md)):

- Deploy infrastructure to your AWS account
- Configure GitHub webhook
- Create test issue with label "approved-for-generation"
- Watch OutcomeOps generate a PR in ~15 minutes

**New to ADRs?** [Start here →](https://github.com/bcarpio/outcome-ops-ai-assist/blob/main/docs/getting-started-with-adrs.md)

**GitHub Copilot / Cursor:** Autocomplete and chat, but no organizational context. Generates generic code requiring manual adaptation to your standards.

**Devin:** Autonomous agent for tasks, but doesn't know YOUR patterns. Still generates code that needs refactoring to match your conventions.

**ChatGPT / Claude (standalone):** Powerful, but requires pasting context every time. Not scalable. No integration with your codebase.

**OutcomeOps:** Ingests YOUR ADRs, YOUR patterns, YOUR standards. AI generates code that already matches your organization. Review outcomes, not syntax.

OutcomeOps was created by Brian Carpio, who previously built:

- **Golden Pipelines (2014)** - Took deployment from 6 weeks → 1 week at Aetna
- **AWS ProServe** - Led largest Healthcare & Life Sciences engagement in ProServe history
- **Platform Engineering** - Before it had a name, building self-service infrastructure at Pearson (2012), Aetna (2014), Comcast (2018)

OutcomeOps applies the same playbook to AI-assisted development:

- Make the easy path the right path
- Bake standards into infrastructure
- Create velocity through automation
- **This is golden pipelines for code generation**

**Getting Started**

- [Getting Started Guide](https://github.com/bcarpio/outcome-ops-ai-assist/blob/main/docs/getting-started.md) - Prerequisites, setup, first steps
- [Getting Started with ADRs](https://github.com/bcarpio/outcome-ops-ai-assist/blob/main/docs/getting-started-with-adrs.md) - Learn about Architecture Decision Records

**Core Documentation**

- [Architecture Overview](https://github.com/bcarpio/outcome-ops-ai-assist/blob/main/docs/architecture.md) - System design and data flows
- [Technical Reference](https://github.com/bcarpio/outcome-ops-ai-assist/blob/main/docs/technical-reference.md) - Detailed technical documentation
- [CLI Usage Guide](https://github.com/bcarpio/outcome-ops-ai-assist/blob/main/docs/cli-usage.md) - Using the outcome-ops-assist CLI
- [Deployment Guide](https://github.com/bcarpio/outcome-ops-ai-assist/blob/main/docs/deployment-guide.md) - Operations and troubleshooting

**Integrations**

- [OutcomeOps MCP Server](https://github.com/bcarpio/outcome-ops-ai-assist/blob/main/docs/mcp-server.md) - Connect Claude Code, VS Code, and other MCP clients
- [SonarQube MCP Server](https://github.com/bcarpio/outcome-ops-ai-assist/blob/main/docs/sonarqube-mcp.md) - Code quality and security tools via MCP

**Compliance**

- [AI Disclosure Modal](https://github.com/bcarpio/outcome-ops-ai-assist/blob/main/docs/ai-disclosure-modal.md) - Pre-use AI transparency notice for regulatory compliance

**Lambda Documentation**

- [Lambda: Query KB](https://github.com/bcarpio/outcome-ops-ai-assist/blob/main/docs/lambda-query-kb.md) - RAG orchestrator (vector search + reranking + answer generation)
- [Lambda: Ask Claude](https://github.com/bcarpio/outcome-ops-ai-assist/blob/main/docs/lambda-ask-claude.md) - RAG answer generation
- [Lambda: Generate Code](https://github.com/bcarpio/outcome-ops-ai-assist/blob/main/docs/lambda-generate-code.md) - AI-powered code generation from issues
- [Lambda: Analyze PR](https://github.com/bcarpio/outcome-ops-ai-assist/blob/main/docs/lambda-analyze-pr.md) - PR analysis orchestration
- [Lambda: Process PR Check](https://github.com/bcarpio/outcome-ops-ai-assist/blob/main/docs/lambda-process-pr-check.md) - PR check worker
- [Lambda: Run Tests](https://github.com/bcarpio/outcome-ops-ai-assist/blob/main/docs/lambda-run-tests.md) - Executes`make test` for generated branches

**Architecture Decision Records**

- [ADR-001: Creating ADRs](https://github.com/bcarpio/outcome-ops-ai-assist/blob/main/docs/adr/ADR-001-create-adrs.md) - How to document architectural decisions
- [ADR Template](https://github.com/bcarpio/outcome-ops-ai-assist/blob/main/docs/adr/TEMPLATE.md) - Template for new ADRs

**For Developers**

- [Claude Guidance](https://github.com/bcarpio/outcome-ops-ai-assist/blob/main/CLAUDE.md) - AI assistant development best practices
- [Backstory](https://github.com/bcarpio/outcome-ops-ai-assist/blob/main/docs/backstory.md) - Why OutcomeOps exists

**Ready to deploy OutcomeOps?**

- **[Learn the Methodology](https://www.outcomeops.ai)** - Understand the OutcomeOps approach
- **[YouTube Channel](https://www.youtube.com/@OutcomeOps)** - Demos and walkthroughs
- **[Learn ADRs](https://github.com/bcarpio/outcome-ops-ai-assist/blob/main/docs/getting-started-with-adrs.md)** - New to Architecture Decision Records?
- **[Technical Documentation](https://github.com/bcarpio/outcome-ops-ai-assist/blob/main/docs/getting-started.md)** - Deployment and implementation guide
- **[Contributing](https://github.com/bcarpio/outcome-ops-ai-assist/blob/main/CONTRIBUTING.md)** - How to get involved
- **Questions & Support** - open an[issue or discussion](https://github.com/bcarpio/outcome-ops-ai-assist/issues)

**Built for engineering velocity.**

Outcome-driven development. Infrastructure by code. Engineering outcomes by AI. Your vision, automated execution.
