Skip to main content
ASP Labs

The AI practice inside a 24-year firm.

At ASP Labs we integrate AI into how we build software. Not as a marketing strategy, but as a tool to tangibly reduce timelines without compromising code quality and documentation.

  • Led by Eric Alfredo Haag
  • Since 2024

AI as an ally to our development team.

Artificial Intelligence has become our development team's best ally, solving most of the recurring problems that historically held back the speed and the quality of every project:

  • Design fidelity, in less time.

    Implementing the design team's visual proposals precisely used to take hours of detailed work from an experienced developer. Today, thanks to the integration between our design tools' MCP servers and our coding agents, that process is far simpler and more direct.

  • Complete documentation, not a pending promise.

    Design, technical and functional documentation — which often ended up incomplete or missing altogether for lack of time — is now generated as a natural part of the workflow.

  • Real test coverage.

    Our test coverage used to reach only a fraction of the code. Today it is exhaustive, rigorous and complete, and it includes automated end-to-end tests at every layer of the system.

  • Boilerplate code in a fraction of the time.

    Writing repetitive, structural code has dropped dramatically, with far higher quality in both functionality and code cleanliness.

  • Security from the first commit.

    Vulnerability scanning stopped being an extra review step and became an integral part of our development methodology.

Eric Alfredo Haag

Head of R&D · ASP Labs Lead

When people say their team uses AI, ask them one question: which specific tool, in which specific part of the workflow, with which measurable outcome. If they can't answer, they're using it the same way you would — occasionally.

Where AI enters, step by step.

Four moments in the development cycle, each with the specific tool and the metric it moves.

01 · Code generation

Code generation with human-in-the-loop

Every senior engineer works with Claude Code integrated into their local environment. For multi-file edits, refactors, and boilerplate, the AI drafts; the engineer reviews line by line before commit. We never merge AI-generated code without human understanding — the goal is throughput without loss of intent. Custom skills are pre-loaded per project (conventions, testing patterns, architectural constraints) so the AI produces code that matches your codebase from the first prompt.

  • Claude Code
  • OpenCode
  • Custom Skills

~40% less boilerplate time

02 · Code review

AI-augmented code review

AI-augmented reviewers run on every PR before a human looks at it: security, performance, and convention-adherence analysis via GitHub Actions. Trivial findings are resolved before a senior spends time on the basics, and human review is reserved for what actually needs judgment.

  • Custom PR bot
  • Semgrep
  • CodeQL
  • MCP servers

80% of trivial findings surfaced before human review

03 · Documentation

Documentation as continuous output

MCP servers connect the AI to your repo and generate docs that stay in sync with the code: ADRs, onboarding guides, OpenAPI specs. Changes are detected automatically, so documentation stops being a debt you pay at the end.

  • MCP servers
  • Claude
  • OpenAPI generator

90%+ of technical docs generated automatically

04 · Test coverage

Test generation and coverage lift

Custom skills generate tests and lift coverage without ceremony. The AI surfaces edge cases a human would miss; humans validate them, they do not replace them. The result is real coverage, not inflated numbers.

  • Custom testing skills
  • Vitest
  • Playwright

42% → 89% coverage in the first sprint

The full stack. No black boxes.

We tell you exactly which tools our engineers use, in which part of the workflow, and why. Transparency about the stack is what separates AI-native practice from marketing.

Terminal agent

Claude Code

Multi-file edits, refactors, and PR drafts in the engineer's terminal.

Terminal agent · OSS

OpenCode

Alternative to Claude Code where open source matters.

IDE

Cursor

Optional — for engineers who prefer an IDE over the terminal.

Context protocol

MCP Servers

Repo-aware AI that reads your codebase, docs, and tickets.

Prompt engineering

Custom Skills

Pre-loaded conventions, testing patterns, and project constraints.

RAG infrastructure

Vector databases

pgvector or Qdrant for client-facing RAG bots.

Orchestration

LangChain / LlamaIndex

Production bot workflows with multi-step reasoning.

App integration

Vercel AI SDK

Streaming AI responses inside production apps.

Security review

Semgrep + rules

Static analysis with custom rules for team-specific patterns.

Metrics and guardrails.

Numbers we track internally. Not because they look good in pitches — because they tell us whether AI is helping or hurting.

~40%

Less boilerplate time

Legacy migration throughput

80%+

AI-assisted test coverage

90%+

Docs generated automatically

<5%

AI bugs escaping to production

100%

Human review on production PRs

What we DON'T do

  • Merge AI code without human understanding
  • Bill AI throughput as senior engineer hours
  • Deploy AI to production without observability
  • Use AI for security-sensitive logic without extra review
  • Sell an AI capability we haven't shipped at least once
  • Hide when AI produced something — attribution is standard

Work with ASP Labs

Book time with Eric.

A deep-technical discussion. Bring your AI questions — the ones vendors won't answer straight.