Pricing

The bot builds it.
An engineer's got your back.

Two ways to work with us. Bot work is fast and yours to verify. With an engineer behind the work, you skip reviewing it yourself, you get senior eyes on it, and you have someone to ping when things change.

First $50 free per workspace — no credit card
The missing piece

AI agents ship fast.
They don't stay around.

The hardest parts of engineering — judgment, ownership, being there later — are the parts current AI agents don't try to do. We added them back.

01
Who reads it before you do?
Current agents don't actually review their own work. They claim it works. You're still the one diffing the PR at midnight.
02
Who catches what'll fail later?
A bot catches typos. It doesn't catch "this'll hit the rate limit when you 10x" — that takes scar tissue.
03
Who picks up when prod breaks?
The bot moved on the second it shipped. When something cracks two weeks later, you're alone on the page.
04
Who says "don't ship this"?
Agents do what you tell them. They don't push back when you're about to shoot yourself in the foot.
Each of these is human work. AI doesn't make it less human — it just made the gap easier to ignore. We added the work back.
What an engineer behind the work actually looks like
🪥
We read it for you
Bot ships, engineer reads before it lands. You skip the review step entirely. The diff that hits your DM has already been looked over.
🧠
Senior eyes catch what bot misses
10+ years of production scars in the loop. Catches "this will break under load" before it ships, not after.
📞
Reachable later
A week from now, a month from now — when something cracks, ping us. The engineer who worked on it picks up. Bot's gone, we're not.
🎯
We tell you when you need help
Most tasks don't need a person — the bot says "I've got this" when that's true. When you genuinely need a human on it, we say that too. The recommendation isn't biased toward our margin.
How the bot routes you

Most things bot handles. Some things, we bring in a person.

You don't pick a tier — the bot does. It reads what you're asking for and routes you to whichever path actually fits the work. Here's what each looks like.

🤖
Most tasks · Bot handles it
Bot just does it
$3 · $10 · $30 · $80
When the ask is clear and the work is well-shaped, the bot takes it async — bug fix, refactor, scaffold, code review. No meeting, no booking. Triggered by a Slack message, finished in your DMs. Most things land here.

What "the bot handles it" looks like

  • Bug fix — single file, well-defined
  • Refactor — within a known codebase
  • Scaffold — new repo, new module
  • Code review — paste a diff or PR URL
  • Tests · docs — write or fill gaps
  • Explain — "what does this function do?"
👥
When it matters · We add a person
We bring in a person
$200 · $500 · $1,500 · $3,000+
When the work needs design, judgment, or someone on call later, the bot pulls you aside and recommends booking time with an experienced engineer. They lead it, write the deliverable, and stay on call. Bot stays in the loop to do prep work so the human time isn't wasted on background reading.

When the bot will recommend a person

  • Solution design — "how should we structure X?"
  • Architecture — framework choice, system boundaries
  • Production deploys — risk, rollback plan, ownership
  • Strategic — pricing, hiring, GTM, framework choice
  • Brand — copy, logo, customer-facing comms
  • Legal — ToS, privacy, contracts

🤖 Without human · Bot Work ladder

Flat prices, not ranges. The bot picks a tier from the request and names the price up front. The bot caps at $80 — anything bigger or judgment-shaped routes to Consulting instead.

ScopeFlat priceExample
Q&A · explain · micro-snippet $0 "what's the diff between map and forEach?" — no quote, just answer
🪶 Micro · one-line tweak, rename, format, translate $3 "rename this var to camelCase", "format this JSON"
🔧 Small · single bug fix · one endpoint · one component $10 "fix the off-by-one in lineNumber.tsx", "add input validation to /api/signup"
🛠 Medium · multi-file refactor · write a module · code review $30 "refactor the date utils to Temporal", "review this 800-line PR"
🏗 Large · new project scaffold · complete feature · SDK integration $80 "scaffold a Next.js admin dashboard with auth + DB"
↗ Beyond Large? → Consulting Anything bigger or that needs design judgment routes to a human

👥 With human · Consulting ladder

Time booked with an experienced engineer. Every session ends with a written deliverable: a decision doc, an architecture sketch, a code review summary, or a strategy memo. Prep work is done by the bot ahead of the session so the human time is spent on judgment, not background reading.

FormatPriceWhat you get
📞 Quick Call · 30 min $200 Sanity-check a small decision · PR review · "is this the right approach?" with one-paragraph written summary
🎯 Solution Design · 60–90 min $500 Architecture for one feature or subsystem · decision rationale · first-step implementation plan
🏗 Design Workshop · half-day (3–4 h) $1,500 System-level design or major selection · decision doc with alternatives · phased roadmap · risk register
🤝 Fractional Engagement · monthly $3,000+ Embedded advisor · weekly sync · async Slack always-on · custom scope. Email cz2440@columbia.edu to scope.

How booking works

When the bot routes you to Consulting (or you ask for it directly), it shows a booking link. You pick the tier, share a few sentences about what you're solving, and our system pages an available engineer. Typical lead time:

  • Quick Call — usually within 24h on weekdays
  • Solution Design — 2–3 business days out
  • Design Workshop — 5–7 business days, dependent on prep
  • Fractional Engagement — kick-off within a week

What flips a task to 👥 Consulting

The bot classifies during the quote step. ANY of these triggers routes you to Consulting (with-human) instead of Bot Work. Multiple triggers don't stack — it's a binary flip.

Production risk
Anything touching prod: deploy, live users, prod DB, config flag rollout, feature toggle. If the user can be affected, a human looks.
Irreversible operation
DB migration, schema change, force push, delete data, uninstall, retract release. Things that hurt if wrong.
Strategic / founder-level
"Should we use X or Y framework?", "what's our pricing for tier 2?", "which engineer should we hire next?", "what's our positioning?"
Brand / customer-facing
Logo, copy on landing pages, customer emails, public posts, investor decks, sales materials. Anything customers see.
Legal / compliance
ToS, privacy policy, GDPR/CCPA, customer contracts, SOC2 evidence, sub-processor agreements.
User explicitly asks
"I'd like an engineer to look at this", "make sure a human signs off", "premium / VIP", "book me a consult". Trust the request.

The decision the bot makes

Every substantial request goes through this. Q&A and tiny edits skip the quote — miniCTO just answers.

User sends a task to miniCTO Is it Q&A or a tiny snippet (≤30 lines)? ├─ yes → just answer · no quote · $0 └─ no → Read ./_account.json (knows free quota + balance) Trigger any Consulting (with-human) criterion? ├─ yes → Quote 👥 Consulting ($200 / $500 / $1500 / $3000+) │ ↓ │ Quote within available? → show booking link → engineer paged on confirm │ Quote > available? → "Top up at <url>, then book your engineer" └─ no → Quote 🤖 Bot Work ($3 / $10 / $30 / $80) Quote within available? → "Approve?" → ship Quote > available? → "Narrow scope or top up at <url>" When the bot's not sure? Give both quotes, let the user pick Don't over-offer Consulting as an upsell — that's bad faith

Real quote shapes

Three examples covering Auto, Human, and ambiguous.

🤖 BOT WORK · CLEAN
you
refactor the date utils into a Temporal-based module
miniCTO
Scoped: refactor src/utils/date/ to use Temporal. About 6 files, similar shape, swap call sites.
🤖 Bot Work · 🛠 Medium · $30 — you have $50 available. Go?
👥 CONSULTING · CLEAN
you
deploy this webhook fix to prod
miniCTO
Scoped: deploy webhook retry fix to production.
👥 Consulting · 📞 Quick Call · $500 — an experienced engineer reviews the diff, does the deploy with you on a call, watches rollout for 30 min, sends a written summary.
Your balance is $50 (free quota). Top up at portal/topup to unlock — once paid, you'll get a booking link.
⚖ AMBIGUOUS · OFFER BOTH
you
should we move from Postgres to PlanetScale?
miniCTO
This is an architectural call — could go either way:
🤖 Bot Work · $30 — I research + write a neutral comparison doc with pros/cons, you decide
👥 Consulting · 🎯 Solution Design · $500 — 60 min with an experienced engineer who'll factor in your stack, scale, and team. You leave with a recommendation + migration plan.
Which?

FAQ

What's "one requirement"?

A single piece of work with a beginning and end. Usually = a Slack thread, or a slash command invocation. If you ask for follow-up changes in the same thread, that's a continuation — no new quote unless the scope materially grew.

Why $50 free per workspace and not per user?

So a team of 20 doesn't get $1000 of free agent time by virtue of headcount. The workspace is the billable unit; the free quota matches.

Does credit expire?

No. Top-up credit rolls over month-to-month indefinitely. If you uninstall, unused credit is refunded.

What if the bot under-quotes?

If real cost ends up under the quoted range, we charge the actual cost, not the quote. If real cost would exceed the quote, the bot pauses mid-work and asks before continuing. We don't surprise you with a bigger bill.

What does Consulting actually include?

Time with an experienced engineer — currently a small bench, growing. For $200 you get a 30-min Quick Call. For $500 you get a 60–90 min Solution Design session. For $1500, a half-day workshop with a written decision doc. Every tier ends with a written deliverable; the call isn't just chat. The bot does prep ahead of the session so the human time is spent on judgment, not status updates.

Who are these "experienced engineers"?

Senior ICs and tech leads with 8+ years building production systems at companies you've heard of. The bench is intentionally small — we don't subcontract to people we wouldn't hire ourselves. Profiles available on request before booking.

Can I always force Consulting?

Yes — just say so in chat. "Book me a consult" or "I'd like an engineer to look at this" routes you to the Consulting flow regardless of what the bot would otherwise quote. Same the other way: if the bot flags Consulting and you want it to just go ahead with Bot Work instead, say "go anyway" — you'll get the bot's output, with no engineer review behind it.

Why is the bot's range a band, not a point?

Software estimates are uncertain. A point estimate would either be too conservative (we leave money on the table) or too aggressive (we'd hit the wall mid-work). The band gives you a realistic expectation; we charge the actual cost within the band.

Is there a monthly subscription option?

Not yet — usage patterns vary enormously per team, so a flat per-seat number doesn't fit anyone. Per-requirement matches what you actually use. If your team scales to "we want unlimited agent time", email and we'll talk enterprise.

Where this lives in the system.

CLAUDE.md teaches the bot this logic per-channel. Triggers, ladders, and quote scripts are all in src/workspaces.js. Update there, then run refresh to push to all channels.

View architecture →