Hire Me
If you’re running production AI and something’s quietly broken, I can help. Three engagement shapes — pick the right surface for your situation.
Free triage call (start here if unsure)
A 30-minute conversation to walk through your stack and identify which tier makes sense — or whether none of them do. No commitment. No deck. Just a real diagnostic chat.
Use this if: - You suspect something’s off but can’t pin it - You’re shopping around between tiers - You want to ask “would this even help me?”
Email: hello@temhan.dev with subject Triage call + 1-2 lines on what’s prompting the question. I reply within 2 business days.
Production AI Audit
A focused review of your production AI deployment against the 35-pattern failure catalog (Field Reference — bundled with the suite). Findings + corrective-action plan delivered within the engagement window.
| Tier | Scope | Investment | Timeline |
|---|---|---|---|
| Audit Lite | One system, top-5 findings, written report | $2,500 | 1 week |
| Audit Standard | Full 35-pattern review, 5 Cs findings, 90-day follow-up | $4,500 | 2-3 weeks |
| Audit + Workshop | Standard + 2-day team workshop + first monthly check-in included | $7,500 | 3-4 weeks |
What you get:
- Written report against the 35-pattern catalog (which patterns are present, which aren’t, severity)
- Specific corrective actions (not “implement monitoring” — exact code changes, hooks, checks)
- 90-day follow-up call (Standard + Workshop tiers)
Email: hello@temhan.dev with subject AI audit inquiry. Include 1 paragraph on your stack + which tier you want.
Custom MCP Build
Adapt the 7 MCP servers I’ve shipped — or build a new server entirely — for your specific stack. Three productized tiers calibrated to honest 2026 LLM-leveraged labor cost.
| Tier | Scope | Investment | Timeline |
|---|---|---|---|
| MCP-Pack Adapter | Fork + tune one of the 7 existing MCPs for your domain (custom prompts, severity rules, log-format adapter) | $2,000 | 3-5 days |
| Custom MCP Server | Purpose-built single-tool MCP for a specific failure-mode in your stack | $10,000–15,000 | 1-2 weeks |
| Production AI Platform | Multi-MCP build, LLM-as-judge backends, persistence, full CI integration, audit-trail | $30,000–45,000 | 4-8 weeks |
What you get:
- Working MCP tested against your real production data (not synthetic fixtures)
- Source code transferred to your repo (not hosted on my infra)
- Documentation + setup walkthrough + 30-day post-ship support
- Optional: open-source the generic version, keep the domain-specific layer private
Email: hello@temhan.dev with subject Custom MCP Build inquiry. Include 1 paragraph on your stack + which tier.
Ops Monitor — ongoing retainer
The other engagement shape: a recurring relationship instead of a one-shot engagement. Best fit if you’ve got production AI and want a trusted-advisor on call without paying audit-tier prices every quarter.
| Tier | Investment | Includes |
|---|---|---|
| Ops Monitor Lite | $500/mo | Quarterly audit (lighter than Audit Lite) · monthly 30-min check-in · Slack channel for ad-hoc questions · priority on the 7-MCP roadmap (your stack’s needs influence what ships) |
| Ops Monitor Standard | $1,500/mo | Everything in Lite + one custom adapter OR tier-prompt update per quarter (rolled into the retainer instead of one-off Adapter engagement) |
Cancel anytime. No annual commitment. Pause for 1-2 months if you’re between projects.
Email: hello@temhan.dev with subject Ops Monitor inquiry. Include 1 paragraph on what you’re running + which tier you’re considering.
How engagements work
- You email with a one-paragraph description of your stack + the tier you’re considering
- I reply within 2 business days with a 30-min discovery call slot (or skip directly to scoping if it’s clear)
- Discovery call confirms scope, timeline, and any red flags. Free.
- One-page SOW sent within 24 hours of the call. You review, send back any redlines.
- Signed SOW + first payment triggers start. I never start work pre-payment.
- Engagement runs with weekly check-ins (or monthly for retainers).
- Deliverables hand-off + 30-day or 90-day follow-up depending on tier.
Average from first email to signed SOW: ~5 business days.
Why this pricing
LLMs collapsed the cost of writing code. They didn’t collapse the cost of judgment, accountability, or relationship. Pricing reflects that:
- Audits stay in the $2.5-7.5k band because the value is pattern recognition + corrective plan, not labor hours
- MCP-Pack Adapter is $2k flat because the work is genuinely 8-hour LLM-assisted in 2026 — anchoring it to old hourly rates would be overcharging
- Custom MCP Server compressed to $10-15k for the same reason — honest about what’s now scriptable vs what still needs human engineering
- Production AI Platform stays at $30-45k because that tier is genuine systems work — LLM-as-judge backends, persistence, audit-trail integration — where human architecture decisions are the actual deliverable
- Retainer at $500-1,500/mo is intentionally low-friction entry because ongoing trusted-advisor is the LLM-immune offer + recurring revenue compounds
You could prompt-engineer most of these yourself in a week with Claude Code. Or pay me a fixed price and have it Friday with my reputation behind it. The choice should be obvious for either path — depending on whether your time is worth more than my fee.
What I don’t do
To be honest about scope mismatch:
- No fixed-price engagements over $45k. Above that, hourly is safer for both of us.
- No subscription / retainer engagements over $1,500/mo until we’ve completed at least one fixed-scope engagement together — proves fit before scaling.
- No “rescue” work without a paid audit first. If you say “we deployed AI, it failed, please fix it” — the right first step is the audit, not skipping straight to fix-it.
- No work without signed SOW + first payment. Verbal “let’s get going” = unpaid work guarantee. Even with good-faith clients.
Common questions
“What stacks have you worked with?”
Production AI deployments across LangChain, LlamaIndex, vanilla SDK calls, custom agent harnesses, OpenClaw, Claude Code, Cursor, Anthropic API, OpenAI API, Gemini, AWS Bedrock. The patterns generalize across all of them — that’s the point of the 35-pattern catalog.
“Do you have references?”
Engagement-specific. Mention in your inquiry email if references matter for your buying process; happy to share once we’re past discovery.
“What if my problem isn’t on the catalog?”
Then we add it. The catalog is a working artifact, not a fixed bible.
“Can you do a free audit so I can decide?”
The free version is the AI Production Auditor Custom GPT — paste your config, get a 5 Cs report. Same methodology, no signup beyond ChatGPT. Useful as a self-serve first pass before commissioning paid work.
For something more tailored: book the free triage call above. It’s 30 minutes; no commitment.
“Why isn’t there an hourly option?”
LLM-leverage punishes hourly billing. It encourages scope creep, rewards slow work, and prices to cost-of-labor instead of value-delivered. Fixed-price + retainer protects both sides — buyer gets a predictable number; I get to use my LLM-leverage without it eating my margin.
“What if my problem is bigger than $45k?”
Then it’s a multi-engagement relationship, not a fixed-price job. Start with an Audit Standard or Production AI Platform tier. Once we’ve worked together once, scaling up gets a lot easier.