Services
One workflow. One number.
Shipped into your stack.
I do not sell an AI strategy. I take a specific manual loop that is costing your team hours, and I replace it with a system that runs in your environment and can be measured against the process it replaced.
Most engagements
4–8 weeks
Fixed-scope agent build
One agent, scoped to one painful workflow, shipped into your stack and running in production.
Who it is for
Platform, SRE and DevOps teams who know exactly which manual loop is burning their week.
What is included
- Discovery: the workflow, the data sources, the failure modes, the success metric
- Architecture with an explicit guardrail and human-in-the-loop design
- Tool/MCP layer over your existing systems — no platform migration
- Evaluation harness so you can prove it works before you trust it
- Deployment into your environment, plus observability on the agent itself
- Handover docs and a working session with the team that will own it
Outcome
A running system with a measured before/after, not a proof of concept that dies in a branch.
Fixed price, quoted after a short scoping call
Also available
Ongoing, no minimum
Hourly consulting
Architecture review, unblocking, and a second pair of eyes from someone who has run agents in production.
Who it is for
Teams already building who need to pressure-test a design, fix an agent that works in demo and fails in prod, or decide whether to build at all.
What is included
- Agent and RAG architecture review
- Evaluation strategy — how you will actually know it works
- Guardrail, permission and human-in-the-loop design
- Model, cost and latency trade-off decisions
- Code review on agent orchestration and tool design
Outcome
Fewer months lost to an architecture that was never going to survive production.
Hourly rate, invoiced monthly
The process
How a build runs
No discovery theatre. The first call is a technical conversation about a specific problem.
Problem statement
A 30-minute call. You describe the manual loop that hurts. I tell you honestly whether an agent is the right answer — sometimes it is a script and I will say so.
Scope and success metric
We agree on one workflow, one measurable outcome, and what the agent is explicitly not allowed to do. Fixed price from here.
Build against your stack
Tool layer over your existing systems, evaluation harness alongside it. You see working software early, not a slide deck at the end.
Ship and hand over
Deployed in your environment, observable, documented, owned by your team. Measured against the number we agreed in step two.
Fit
When not to hire me
If a cron job and forty lines of Python solve your problem,
I will tell you that on the first call.
Probably not a fit
- You want a chatbot on your marketing site.
- The goal is an AI announcement rather than a measured outcome.
- The workflow changes every week and nobody can define what correct looks like.
- You need a full in-house AI team stood up — that is a hire, not an engagement.
Strong fit
- Your on-call engineers spend the first twenty minutes of every incident gathering context.
- Institutional knowledge is somewhere in Confluence and nobody can find it.
- You have observability tooling that only three people know how to query.
- You built an agent, it demoed well, and it is not trusted in production.
I work alongside a full-time engineering role, which is why I take one build engagement per quarter. That constraint is deliberate: it means the engagement I am in gets real attention rather than a slice of it. If the timing does not work, I will say so rather than stretch.
Limited availability
Tell me the problem.
I’ll tell you if an agent is the answer.
A 30-minute call, no pitch. Describe the manual loop that hurts and I’ll give you a straight read on whether this is worth building — including when the honest answer is a script, not an agent.
30 minutes · video call · no pitch