Jeff Rogers · Atriumn

Engineering leadership for teams building with AI.

Twenty-five years building software and the teams behind it, at Thoughtworks, Groupon, Angie's List, Centro, Tempus AI and Pinger. Today I work with founders and engineering leaders as a fractional CTO, advisor or hands-on builder, and I build my own products, starting with Idynic.

Book an intro call See what I'm building

445 PRs merged this week by my agent build loop

Live from the build loop

Shipping right now.

Issues go in, reviewed pull requests come out. Every row is a real build by the agent pipeline I run, with what it cost and how many tries it took.

How the loop works →

PRs merged, last 7 days: 445
agent builds shown: 40
verified on the first try: 10%
median compute per build: $0.82

Sun 10:30pIdynicShipped a featurefeaturesonnet43 tool calls3 test runs≈$0.74merged
Mon 12:20aRunbookAdded new pages with an editor and viewfeatureopus64 tool calls5 test runs≈$2.49revising
Sun 10:31pRunbookAdded new mobile screens and editingfeatureopus214 tool calls3 test runs≈$11.23revising
Mon 1:05aIdynicAdded an authentication integrationfeatureopus164 tool calls11 test runs≈$7.09revising
Mon 12:35aIdynicShipped a featurefeatureopus120 tool calls9 test runs≈$4.61revising
Sun 9:55pRunbookFixed a form state bugfixopus27 tool calls2 test runs≈$0.82verified · try 4
Sun 8:55pRunbookAdded a new api with client supportfeatureopus13 tool calls1 test run≈$0.53verified · try 2
Sun 8:35pRunbookAdded a new form inputfeatureopus21 tool calls2 test runs≈$0.68revising
Sun 7:55pRunbookShipped a featurefeatureopus41 tool calls2 test runs≈$1.14revising
Sun 8:05pRunbookAdded a new api with client supportfeatureopus53 tool calls4 test runs≈$1.60revising
Sun 7:26pRunbookShipped a featurefeatureopus225 tool calls5 test runs≈$9.50revising
Sun 5:50pRunbookShipped a featurefeatureopus31 tool calls0 test runs≈$1.24verified · try 6
Sun 4:30pRunbookAdded a mobile screenfeaturesonnet40 tool calls2 test runs≈$0.73verified · try 3
Sun 3:35pRunbookAdded a main screenfeaturesonnet12 tool calls0 test runs≈$0.21revising
Sun 2:50pRunbookAdded AI supportfeatureopus23 tool calls0 test runs≈$0.74verified · try 2
Sun 2:16pRunbookAdded a new mobile viewfeaturesonnet70 tool calls0 test runs≈$1.37revising
Sun 2:06pRunbookAdded AI outputfeatureopus39 tool calls0 test runs≈$1.84revising
Sun 1:23pBuild loopRan the build loop's self-testself-testhaiku12 tool calls1 test run≈$0.01verified · try 2
Sun 1:22pBuild loopRan the build loop's self-testself-testhaiku15 tool calls1 test run≈$0.01failed
Sun 1:21pBuild loopRan the build loop's self-testself-testhaiku17 tool calls1 test run≈$0.02revising
Sun 3:45pRunbookShipped a featurefeatureopus2 tool calls0 test runs≈$0.35revising
Sun 3:37aBuild loopRan the build loop's self-testself-testopus5 tool calls1 test run≈$0.34failed
Sun 3:36aBuild loopRan the build loop's self-testself-testhaiku9 tool calls2 test runs≈$0.01revising
Sun 3:35aBuild loopRan the build loop's self-testself-testhaiku15 tool calls1 test run≈$0.01revising
Sun 3:34aBuild loopRan the build loop's self-testself-testhaiku5 tool calls1 test run≈$0.01revising
Sun 3:35aBuild loopRan the build loop's self-testself-testhaiku13 tool calls1 test run≈$0.01revising
Sun 3:33aBuild loopRan the build loop's self-testself-testhaiku18 tool calls1 test run≈$0.02revising
Sun 3:33aBuild loopRan the build loop's self-testself-testhaiku16 tool calls1 test run≈$0.02revising
Sun 5:42aRunbookAdded a data workflowfeatureopus53 tool calls3 test runs≈$1.18revising
Sat 3:46pRunbookShipped a featurefeatureopus26 tool calls2 test runs≈$0.91revising
Sat 3:30pRunbookShipped a featurefeaturesonnet21 tool calls0 test runs≈$0.35verified · try 3
Sat 2:35pRunbookAdded a review stepfeatureopus22 tool calls0 test runs≈$1.41verified · try 3
Sat 3:20pRunbookShipped a featurefeatureopus185 tool calls8 test runs≈$9.34revising
Sat 1:50pRunbookShipped a featurefeaturesonnet14 tool calls0 test runs≈$0.22revising
Sat 1:41pRunbookAdded an AI output stepfeatureopus61 tool calls1 test run≈$2.23revising
Sat 1:25pRunbookAdded a screen stepfeaturesonnet87 tool calls0 test runs≈$1.38revising
Sat 1:11pRunbookAdded a new input flowfeatureopus129 tool calls1 test run≈$9.69revising
Sat 10:50aRunbookAdded a new data screenfeatureopus15 tool calls1 test run≈$0.55verified · try 2
Sat 10:25aRunbookShipped a featurefeatureopus105 tool calls6 test runs≈$3.58verified
Sat 10:10aRunbookShipped a featurefeatureopus97 tool calls5 test runs≈$4.86revising

Sun 10:30pIdynicShipped a featurefeaturesonnet43 tool calls3 test runs≈$0.74merged
Mon 12:20aRunbookAdded new pages with an editor and viewfeatureopus64 tool calls5 test runs≈$2.49revising
Sun 10:31pRunbookAdded new mobile screens and editingfeatureopus214 tool calls3 test runs≈$11.23revising
Mon 1:05aIdynicAdded an authentication integrationfeatureopus164 tool calls11 test runs≈$7.09revising
Mon 12:35aIdynicShipped a featurefeatureopus120 tool calls9 test runs≈$4.61revising
Sun 9:55pRunbookFixed a form state bugfixopus27 tool calls2 test runs≈$0.82verified · try 4
Sun 8:55pRunbookAdded a new api with client supportfeatureopus13 tool calls1 test run≈$0.53verified · try 2
Sun 8:35pRunbookAdded a new form inputfeatureopus21 tool calls2 test runs≈$0.68revising
Sun 7:55pRunbookShipped a featurefeatureopus41 tool calls2 test runs≈$1.14revising
Sun 8:05pRunbookAdded a new api with client supportfeatureopus53 tool calls4 test runs≈$1.60revising
Sun 7:26pRunbookShipped a featurefeatureopus225 tool calls5 test runs≈$9.50revising
Sun 5:50pRunbookShipped a featurefeatureopus31 tool calls0 test runs≈$1.24verified · try 6
Sun 4:30pRunbookAdded a mobile screenfeaturesonnet40 tool calls2 test runs≈$0.73verified · try 3
Sun 3:35pRunbookAdded a main screenfeaturesonnet12 tool calls0 test runs≈$0.21revising
Sun 2:50pRunbookAdded AI supportfeatureopus23 tool calls0 test runs≈$0.74verified · try 2
Sun 2:16pRunbookAdded a new mobile viewfeaturesonnet70 tool calls0 test runs≈$1.37revising
Sun 2:06pRunbookAdded AI outputfeatureopus39 tool calls0 test runs≈$1.84revising
Sun 1:23pBuild loopRan the build loop's self-testself-testhaiku12 tool calls1 test run≈$0.01verified · try 2
Sun 1:22pBuild loopRan the build loop's self-testself-testhaiku15 tool calls1 test run≈$0.01failed
Sun 1:21pBuild loopRan the build loop's self-testself-testhaiku17 tool calls1 test run≈$0.02revising
Sun 3:45pRunbookShipped a featurefeatureopus2 tool calls0 test runs≈$0.35revising
Sun 3:37aBuild loopRan the build loop's self-testself-testopus5 tool calls1 test run≈$0.34failed
Sun 3:36aBuild loopRan the build loop's self-testself-testhaiku9 tool calls2 test runs≈$0.01revising
Sun 3:35aBuild loopRan the build loop's self-testself-testhaiku15 tool calls1 test run≈$0.01revising
Sun 3:34aBuild loopRan the build loop's self-testself-testhaiku5 tool calls1 test run≈$0.01revising
Sun 3:35aBuild loopRan the build loop's self-testself-testhaiku13 tool calls1 test run≈$0.01revising
Sun 3:33aBuild loopRan the build loop's self-testself-testhaiku18 tool calls1 test run≈$0.02revising
Sun 3:33aBuild loopRan the build loop's self-testself-testhaiku16 tool calls1 test run≈$0.02revising
Sun 5:42aRunbookAdded a data workflowfeatureopus53 tool calls3 test runs≈$1.18revising
Sat 3:46pRunbookShipped a featurefeatureopus26 tool calls2 test runs≈$0.91revising
Sat 3:30pRunbookShipped a featurefeaturesonnet21 tool calls0 test runs≈$0.35verified · try 3
Sat 2:35pRunbookAdded a review stepfeatureopus22 tool calls0 test runs≈$1.41verified · try 3
Sat 3:20pRunbookShipped a featurefeatureopus185 tool calls8 test runs≈$9.34revising
Sat 1:50pRunbookShipped a featurefeaturesonnet14 tool calls0 test runs≈$0.22revising
Sat 1:41pRunbookAdded an AI output stepfeatureopus61 tool calls1 test run≈$2.23revising
Sat 1:25pRunbookAdded a screen stepfeaturesonnet87 tool calls0 test runs≈$1.38revising
Sat 1:11pRunbookAdded a new input flowfeatureopus129 tool calls1 test run≈$9.69revising
Sat 10:50aRunbookAdded a new data screenfeatureopus15 tool calls1 test run≈$0.55verified · try 2
Sat 10:25aRunbookShipped a featurefeatureopus105 tool calls6 test runs≈$3.58verified
Sat 10:10aRunbookShipped a featurefeatureopus97 tool calls5 test runs≈$4.86revising

Hover to pause. Failures and send-backs stay in the feed.

How I help

Fractional CTO / VP Engineering

Part-time technical leadership: strategy, hiring, architecture and delivery, two to three days a week.

Best for: Series A-C startups scaling from 5 to 50 engineers

Technical Advisory

Regular sessions with founders and engineering leaders on the decisions that shape the team and the platform.

Best for: Founders and eng leaders navigating critical inflection points

Project Consulting

Time-boxed engagements on one hard problem: an AI integration, a migration, a delivery bottleneck.

Best for: Teams facing a specific technical challenge with a deadline

How engagements work →

Now building

Products and platforms I'm building at the intersection of engineering and entrepreneurship.

Everything I've built →

Idynic

Founder

Active

product

An AI career-identity platform. It turns a work history into an evidence-backed profile, then generates tailored résumés, cover letters and recruiter-facing pages from it. Solo-built, and this site runs on it.

Learn more →Visit site ↗

Sabir Homes

Founder

Pre-launch

service

A home maintenance and concierge service for homeowners.

Learn more →

Ultimate Ninjas

Co-Owner

Active

service

A youth fitness business I co-own, where I run program operations, curriculum and customer experience.

Learn more →

This site is generated live from my Idynic profile.

What Clients Say

A few words from the people I've had the privilege of building with.

AI application development

Jeff has been an invaluable technical partner. The AI-powered tools he built helped us demonstrate real-world value to customers faster than I thought possible. He understands the sales cycle and delivers production-quality software on startup timelines.

Matt P.

Founder & Lead Investor · Sabir Homes

Custom platform development

I came to Jeff with a messy set of manual workflows and walked away with a platform that actually runs my business. He asked the right questions, moved fast, and built something my team adopted immediately. Worth every dollar.

Jamiel S.

Founder · Property Management

Fractional engineering leadership

Jeff joined us as a fractional technical lead at a critical moment — we were under deadline pressure to deliver a government proposal platform and needed someone who could architect it right and get it across the finish line. He did both, and the quality of the work gave us real credibility with our first clients.

Brian R.

CEO · GovTech Startup

AI advisory

Jeff has been an indispensable AI advisor for our team. He cuts through the noise and keeps us oriented on what actually matters in the AI ecosystem — the right tools, the right timing, and how it all applies to our business. His guidance has shaped how we think about our product roadmap.

Justin U.

CEO · Document Storage

Have a team or a product that needs a senior hand?

Book an intro call