Bring me a project. I'll tell you honestly what it'll take and what it'll cost.
Ten years at shipping production software, sixteen months in daily agentic AI development with Claude Code, MCP, and adjacent tooling. A deep well of experience to draw from, depending on what the project needs.
What I do
Full-stack engineer and system designer. Ten years shipping production software at eBay (SE2 to MTS2), and sixteen months building agentic workflows, MCP tooling, and adversarial review systems with Claude, ChatGPT, and Claude Code. Along the way I've also shipped APIs, desktop apps, data pipelines, and a lot more across the stack. I take on projects AI or not, and I scope every engagement honestly before you commit to anything.
What I take on
I'll consider most engagement shapes, as long as the scope is something I can deliver well and the problem is interesting enough to earn my attention. I've built production AI agents, MCP servers and protocol tooling, full-stack web apps, desktop and mobile applications, APIs, data and research pipelines, graph-backed knowledge systems, and plenty more.
I've worked in domains from e-commerce and Shopify platform integrations to EEG and neuroscience data, from document processing pipelines to multi-agent safety systems. If you're not sure whether your project is a fit, ask me. I'd rather have the conversation than have you self-reject.
Who this is for
Founders, accelerator-backed companies, and small product teams who want one senior engineer to own a defined piece of work and ship it. Every engagement has a scope, an outcome, and an end date.
If you need an open-ended seat on the team, a long-term contractor relationship, or to navigate an RFP or procurement cycle, I'm probably not the right fit.
Ways to work together
Five tiers, from a free async second opinion through to full builds. Pick the one that fits your scope, or reach out and we'll figure it out together.
💡
Idea Review
Free. Async. One-pager.
Free while my schedule has room. This tier closes when I'm near capacity.
For ideas you want a second opinion on before committing time or money.
What you walk away with
A one-pager with my honest take on whether the idea is worth pursuing
What has to go right for it to work, and what's most likely to kill it
A rough technical direction: the shape of system this would be, what's likely the hard part, and a rough sense of the build effort
Comparable patterns I've seen succeed or fail, so you can learn from what's already happened in the space
A light competitive landscape: what already exists, the closest alternatives, and any tools worth evaluating before building from scratch
A clear lean: pursue it yourself, move to a paid Review & Spec, or set it down
The reasoning visible, so you can stress-test it before making a call
This stops at the concept level. I won't deliver an architecture sketch, a detailed spec, or sequenced priorities at this tier. That's what Review & Spec is for.
Same engagement in two sizes. Standard is the fast path for problems with a clear shape. Extended is for larger systems, projects with significant existing code to work around, or when multiple architectural directions need to be compared before committing.
Both produce a written, buildable spec your team can act on. Not sure which? Describe the problem and I'll tell you.
Standard
2 weeks. $2,500 fixed.
For one system, one team, one decision.
What you walk away with
A written review of your system or problem, including the parts I'm unsure about, why, and what would resolve them
A spec covering the path I'd recommend: priorities, sequencing, an architecture sketch, and the open questions to resolve before build
Where a recommendation rests on a specific benchmark, doc, or prior result, I cite it. Where I'm relying on judgment, I say so
A call to walk through the spec and answer whatever's left
The discovery captured in writing, so your team can build from it directly or bring it back to me without redoing the work you just paid for
Extended
3–4 weeks. From $5,000.
For larger systems, projects with significant existing code to work around, or when multiple architectural directions need to be compared before committing.
What you walk away with
Everything in Standard, plus more surface area and more back-and-forth:
A comparative analysis of the architectural directions worth considering, with the tradeoffs visible so a future engineer can see why this path was chosen over the others
A deeper pass through your codebase, infrastructure, or product
Working sessions through the engagement, not only at delivery
A phased rollout plan, where the build is large enough to require sequencing across releases
A non-technical summary for sharing with non-engineering audiences
🔧
Review & Build
1 week review + 2–8 weeks build. From $5,000.
Bundled below buying Review & Spec Extended and Build separately.
When you've decided to build and want the spec and the implementation in one engagement.
What you walk away with
Phase 1 (1 week review)
A build-ready spec sized to the decision in front of us. Phase 1 is scoped to the build, not as a standalone deliverable. If you're not sure you want to build, start with Review & Spec
The path I'd recommend, with the alternatives I considered briefly noted
Acceptance criteria you sign off on before any code gets written
A go/no-go decision point at the end of Phase 1. If the spec uncovers something that changes the build decision, you've paid for the review only, and we part cleanly
Phase 2 (2–8 weeks build)
Same deliverable shape as the Build tier below: implementation shipped against the agreed acceptance criteria, tests on the parts most likely to break in production, written handoff, and a walkthrough call.
🚀
Build
2–12 weeks. From $2,000.
You have a spec, a description, or a half-built prototype. I scope it from whatever you bring, agree a fixed price and timeline in writing, then build. The floor sits below Review & Spec Standard because the discovery is already done. You're paying for execution, not analysis.
What you walk away with
A written scope and price agreed before any code gets written, with feedback on anything in your spec or prototype I'd flag before committing
The implementation shipped against the acceptance criteria we agreed on
Tests on the parts most likely to break in production, agreed in the scope before I start
A written handoff covering the architecture, integration points, failure modes I'd watch, and the decisions a future engineer will need context on
A walkthrough call to transfer the system to your team
If scoping reveals the problem isn't build-ready, I'll point you to Review & Spec and credit the time already spent toward Standard. No double-billing.
Every engagement is fixed scope, fixed price, agreed in writing before I start work. Here's how I get to a number:
Size of work matters more than hours. I look at how much real thinking, writing, and building the problem takes, not at my clock.
Risk matters. Work where I can predict the outcome is priced lower than work where I can't. If we both agree the problem is well-defined, the price reflects that.
Leverage matters. If I can reuse patterns I've already built (CLAUDE.md specs, review pipelines, MCP tooling, session-mining plugins), you get the benefit of that leverage in the price.
Your stakes matter. A fix on a solo builder's side project is priced differently than the same fix on a production system serving real revenue. Not because the work is different, but because the value is.
I name my uncertainty. If I don't know how long something will take, I say so and either scope smaller or break the engagement into phases with their own numbers.
Fixed scope, not hourly. I don't bill time and materials. It rewards slow work and punishes efficiency, and neither of us wants that.
About my pricing
A note on the numbers. These are my current engagement prices, and they're lower than what the market typically charges for this kind of work. I'm deliberately pricing on the low end while I build out my public track record with new clients. Ten years shipping production software plus sixteen months deep in agentic development is real, but I'd rather earn the market rate than assume it. After a handful more engagements I'll raise these to match the specialization. If you want to work together while the numbers are still here, now is a good moment.
If your budget is below these ranges, tell me anyway. I'd rather have an honest conversation and find out we're not a fit than lose both our time to a guessing game.
What I commit to on every engagement
Fixed scope, fixed price, in writing within 5 business days of our first call. If the scope changes mid-engagement, we stop and rescope together. No silent expansion.
You own everything I deliver. Code, documents, plugins, specs. Unrestricted. I retain the right to anonymize and cite patterns in public writing. You review and redact before anything goes public.
Your data stays local unless you explicitly say otherwise. Any session history mining runs on your machine.
Every written deliverable goes through my 4-agent review pipeline (fact-checker, technical reviewer, editorial reviewer, consistency reviewer) before you see it. Same pipeline I run on every blog post I publish.
Honest disagreement. If I see something I think will hurt you later, I'll tell you directly and back it up with specifics. My job is to help you succeed, not to agree with you.
No hidden uncertainty. If I don't know something, I say so. If something is outside my depth, I tell you and help you find someone better suited.
Fair exit. Review engagements have a pro-rated exit point in the first 5 business days. Build engagements are broken into phases, and you can stop at any phase boundary with a clean handoff. I don't lock people in.
My guarantees
The remedies below describe what I commit to in every paid engagement. They become binding only when reproduced in the signed engagement letter, which is the full and integrated agreement. Specific mechanics, notice windows, hour caps, exit terms, dispute resolution, and client obligations are defined there.
Acceptance criteria. Every paid engagement has acceptance criteria written down before I start. If a deliverable fails to do what we agreed it would do, I keep working through a bounded set of revision rounds at no additional cost. Non-critical issues (cosmetic, polish, or scope-adjacent requests) are addressed when reasonable or scoped as a new engagement.
Review pipeline rework. If a written deliverable has a factual or technical error you can demonstrate, I rework that section at no cost. Notice window is defined in the engagement letter.
First-phase milestone. Build and Review & Build engagements run in phases with named milestones and dates. If I miss the first milestone date, you can reset scope and dates with me, or exit with a refund of the unearned phase fee. Documented client-side delays toll the deadline.
Build credit. If Build scoping reveals the problem isn't build-ready, I'll point you to Review & Spec, and the time already paid for during scoping credits toward Standard.
The signed engagement letter is the binding agreement. The language above describes my standard practice.
Standard with every engagement
The items below appear in every paid engagement letter, in this language. Specific bounds and mechanics are defined there.
30 days of async support after delivery. Within 30 days of delivery, I'll respond async to bug reports and clarification questions about what I shipped, typically within one business day. New scope, follow-up features, or adapting the work to new contexts is a separate engagement.
A "what comes next" note. With every final deliverable, I include a short written note on the natural next step I see, whether that's a Phase 2 with me, an internal extension your team can run, or a different vendor entirely. Separate from the technical handoff, which covers the system itself.
Deliverables in your team's format. Notion, Linear, Confluence, GitHub, Google Docs, or markdown. If your team uses something else, we'll find a format that imports cleanly.
A review of your AI coding sessions, if applicable. If you share an export of recent Claude Code or Cowork sessions, I'll return a one-page note identifying two or three recurring patterns worth tightening. Scope: up to ~20 sessions per engagement. Draws on capabilities documented in the session-schema and conversation-mapping posts.
Track record
Portland State University (active client engagement) — software engineering services on the Akaya knowledge management pilot, an AI-native platform that captures tacit team knowledge via voice and turns it into searchable playbooks, how-tos, and learning cards with citations. Akaya is a 2026 cohort company in the Oregon AI Accelerator. Through Dec 2026.
ShopForge — Production AI agent running a live Etsy shop end-to-end for 16 months. 34 specialized skills, three-tier memory, intent-based architecture that cut automation code 74%. The flagship proof that I build systems that survive real production, not demos. Case study →
Reverse-engineered Cowork session format — Documented Anthropic Cowork's undocumented session storage across 146 files and mapped conversation layout across 195 sessions. This is the capability that lets me mine your Claude Code and Cowork history for patterns during a review. Session schema , conversation mapping .
MCP API Bridge — Released, MIT licensed, 74 tests. A production-quality starter kit for turning any REST API into an MCP server. Shipped with docs, a reference implementation, and a working demo.
Upstream bug reports — Filed and acknowledged bug reports on Google's Gemini SDK and Anthropic's Claude Code (#32561, #32213). Third-party validation that I find real problems in real tools.
4-agent review pipeline — The same fact-checker / technical reviewer / editorial reviewer / consistency reviewer pipeline I run on every blog post is what I'll run on your deliverables. See the process in action across 18 published posts , including self-retracted findings and corrections.
10 years at eBay (SE2 to MTS2) — Mobile Web, Charity, Android Native, View Item, and Ads. Full-stack production systems serving millions of users daily. See the full timeline on the experience page .
Before you reach out
"I'm not sure which tier fits my project."
That's fine. Pick "Not sure" on the form and describe what you're working on. I'll tell you what I think.
"What's the difference between Idea Review and Review & Spec?"
Idea Review is free, async, and stops at viability (should you do this?). Review & Spec is paid and goes into the buildable details (how should you do this?). If you're not sure which you need, start with Idea Review.
"Is there a cost to the first meeting?"
No. If we move to a paid engagement, we'll schedule a meeting to discuss scope. No sales funnel, no drip.
"How fast do you respond?"
Within 2 business days for any inquiry. Idea Review one-pagers ship within 5 business days of submission while my schedule has room.
"What if my project isn't AI-related at all?"
Still reach out. I'm a full-stack engineer first. Some of the best projects I've shipped have nothing to do with AI.
"What happens to my data?"
Anything you share during our conversations stays confidential. Anything I'm given access to during an engagement stays on your systems unless you explicitly say otherwise. I never use client work in public writing without your review and approval.
Start a conversation
Inquiry sent.
I'll reply within 2 business days. If we're not a fit, I'll tell you honestly and refer out when I can.
Something went wrong.
Please try again or email me directly at hello@brycewatson.com.
I reply within 2 business days. If we're not a fit, I'll tell you honestly.
