← Ways to work with me

Taking on one reliability engagement

I keep AI agent systems reliable after they ship.

For small AI teams with a critical browser agent or tool-using workflow already in use. I find the failures hiding behind the demo, build evidence around them, and make recovery part of the system.

20-minute technical conversation · paid diagnostic first · no sales theatre

critical workflow / run 0842 observed
  1. 01
    Goal acceptedscope and evidence target fixed
    pass
  2. 02
    Tool callbrowser state changed as expected
    pass
  3. 03
    Result driftpage changed; expected control missing
    caught
  4. 04
    Recovery pathbounded retry preserved prior work
    recovered
  5. 05
    Independent checkoutcome verified outside agent report
    pass

This is for you if

Your agent has real users, real tool calls, and failures that cost engineering time or customer trust.

browser agents research automation tool-using workflows private AI systems

Where the work starts

The failures that appear after the clean demo.

Browser and tool drift

Selectors, permissions, rate limits, and third-party behavior change underneath the workflow.

Recovery that loses the run

A retry starts over, repeats side effects, or discards the evidence needed to understand what happened.

Confident but unverifiable output

The agent reports success without a source, artifact, or independent check that proves the task completed.

Silent cost and latency regressions

A workflow still finishes, but uses more model calls, takes longer, or becomes operationally expensive.

The low-risk starting point

Start with a paid reliability diagnostic.

Before a retainer, I map the system around the workflows that matter most. The result is a bounded baseline: what fails, how to reproduce it, what is already protected, and what should change first.

Describe your system →
01

Critical journey mapUp to three workflows, their dependencies, and their actual success conditions.

02

Failure reproductionConcrete examples, logs, and the smallest repeatable cases behind the instability.

03

Reliability baselineRegression gaps, recovery gaps, and observable cost or latency risks.

04

Prioritized planA decision-ready sequence of fixes, with retainer scope only if ongoing work makes sense.

Ongoing engagement

A narrow retainer, built around evidence.

starting at $5,000 per month · 90-day initial term
Baseline

Regression coverage for the agreed critical workflows.

Weekly

A concise failure, drift, and operating-risk report.

Monthly

One agreed reliability improvement shipped and verified.

Incidents

Bounded investigation, recovery support, and a useful postmortem.

Handoff

Operator documentation and checks your team can keep using.

What the retainer is

Focused ownership of one agreed reliability surface, with business-hours collaboration and explicit monthly priorities.

What it is not

Unlimited feature development, 24/7 on-call support, a replacement CTO, or a promise that no failure will ever happen.

Public evidence

The offer comes from systems I already build and test.

The public proof shows the engineering approach. Private client systems stay private.

This is a newly focused service offer. The examples above are public systems work, not disguised client logos. A diagnostic establishes the evidence and scope for your system before either side commits to an ongoing engagement.

One useful first message

Tell me what is running, where it breaks, and what success needs to mean.

contact@phnix.dev

Remote · Toronto · one new engagement available