Home

Services

I help technical teams adopt AI-first development workflows and build agentic systems. In both cases, the work is finished only when the result is safe to run in production.

AI-First Development Adoption

Your developers already use Claude Code and Cursor to generate features, refactor modules and fix bugs in synchronous sessions. That's Level 1. At Level 3, multiple autonomous agents pick up backlog issues and open PRs with evidence for human review. Reaching that level requires trust: confidence that agent output is reliable enough for production. That trust comes from three enablers.

The Three Enablers of Trust

Foundations

CI/CD pipelines that run on every PR. Unit tests, integration tests, end-to-end tests with Playwright. Containerized environments with Docker so agents and developers work in identical setups. Code quality gates that keep the codebase navigable for both humans and AI. Without these foundations, letting autonomous agents loose on your codebase is a liability.

Capillary Knowledge Base

Agents can read code, but they can't infer business rules or conventions that were never written down. A capillary knowledge base records that project-specific context in structured skills, close to the modules where agents need it.

Observability

When an async agent completes a task, the engineer reviewing it needs more than a diff. For frontend changes, the agent generates a video walkthrough. The engineer watches it on their phone and evaluates in seconds, without pulling the branch. Complementary to automated testing: CI catches regressions, the video handles the human judgment layer.

Level 3 works only when foundations, a project knowledge base and observability are available together. Without project knowledge, agents can pass CI while missing business requirements. Without observability, reviewers cannot verify what the agents did.

How the Engagement Works

1

Assessment

I audit your current development workflow. Where are the gaps that would make autonomous agents risky? Missing tests, no CI pipeline, manual deployments, undocumented business rules? I map out which trust enablers are missing and what needs to change before agents can be relied on.

2

Trust Infrastructure

I set up (or upgrade) the three enablers: CI/CD with automated testing, containerized environments, staging for safe validation, a capillary knowledge base that translates unwritten rules into agent-readable skills, and observability pipelines for agent output verification.

3

Agent Workflow Adoption

I introduce agents into the team's workflow, starting at Level 1 (synchronous sessions for architecture and complex features) and progressing to Level 2-3 (autonomous agents handling bug fixes, small features, and maintenance in parallel). I configure the orchestration layer and establish review processes for agent-generated PRs.

4

Autonomy

The goal is that I leave and your team keeps going. They have the trust infrastructure in place. Async agents pick up work from the backlog. CI catches mistakes. The knowledge base keeps agents grounded. Observability lets engineers verify results quickly.

Who This Is For

  • Software companies with 3-30 developers who haven't fully integrated AI into their workflow
  • CTOs who see the productivity potential but worry about quality and reliability
  • Teams already using Claude Code and Cursor but stuck at Level 1 (synchronous), without autonomous agents running in parallel
  • Companies on legacy codebases where the fear of AI-introduced regressions is highest

Agentic Systems & Integration

I design agentic systems where AI agents work with your existing tools, data and processes. I define what the agents may do, account for compliance requirements and log their actions for review.

Voice AI

Real-time voice assistants that integrate with your existing systems. Cascade pipelines with full observability into transcription, reasoning, and speech synthesis. I've built production voice assistants handling appointment booking, CRM queries, and multi-system orchestration.

Workshop booking case study

Workflow Automation

Multi-agent systems that generate and execute complex workflows from natural language. Designed for domains where auditability matters: every step is logged, every decision is traceable, every execution is reproducible.

Workflow builder case study

Data Pipelines

I build pipelines that turn portfolio or CRM data into specific alerts and reports. The system flags patterns and risks that a manual review would miss.

Custom Integrations

I connect AI systems to Google Workspace, Slack, WordPress, CRMs, ERPs and domain-specific platforms, with the validation and logging needed for production use.

Blockchain agent case study

Ready to talk?

I work on short-term contracts (1-6 months), 2-4 days per week, remotely with clients worldwide.

Book a consultation