Olu Akele / Portfolio 2026Now building: ShelfReadyPrefer the technical details? Flip this.

Built to multiply output. Built with AI, tested for real.AI-built, eval-proven.

Olu Akele smiling, arms crossed, in a cream polo against a pink backdrop

I'm a product manager who builds with AI. I take messy, complicated problems, make them simple, build the fix, and test it so the results are real, not just a nice demo.I build solutions that multiply what a team can ship, lift performance, and solve the customer problem in front of them. Every build is measured with evals and documented in public, so the results are honest and the work moves faster.

Focus
AIs that do tasks for you, not just answer questions. that do real work, tested before they shipAI-built products, agents, evals
SCROLL FOR THE WORK * 1 SHIPPED * 4 NEXT *

Case studies

1 shipped, 4 in the queue. Real numbers only
99.3% AI-ready99.3% agent-readyup from 78% after 105 approved fixes
78%99.3%BEFOREAFTER

How many products an AI shopping assistant can fully understand. Before: the store as it was. After: 105 fixes, each one checked by a person.Share of products an AI shopping agent can read fully. Before: the original catalog. After: 105 fixes, each approved by a person.

ShelfReady

Build 01 · Live
Helping online stores get found by AI shopping assistantsAI agents + MCP + Shopify / agent-ready storefront
Problem
More people now ask an AI assistant to shop for them. When a product's details are vague or missing, the assistant skips it, and the store never knows why.AI shopping agents skip products when catalog data is vague or missing, and merchants can't see the gap.
Bet
Check every product the way an AI shopper would, fix what's missing, and have a person approve each change. Then test real AI shopping before and after.Audit every product for agents, fix it with a human approving each change, then measure real agent shopping before and after.
Result
Almost every product is now fully readable by an AI shopper: 99.3%, up from 78%. In 360 test shopping trips, the AI never bought the wrong item.105 approved fixes took agent-ready products from 78% to 99.3%. In a 360-session shopping test across both catalogs, the AI agent never bought the wrong product.
PlannedBuild 02

Red Pen

Build 02 · Planned
A support-reply writer with a built-in graderLLM + RAG + Python / eval harness
Problem
AI can write support replies that sound great but get facts wrong. Nobody knows how often.AI-drafted support replies read well and still get facts wrong, and nobody can say how often.
Bet
Write the test first: practice questions with known answers. Then improve the AI one change at a time and keep only what raises the score.Build the eval set first, then change one prompt at a time and keep only what moves the score.
Result
Planned: a score for each version of the AI, and a bar it must pass before it goes live.Planned: pass rate per prompt version against a ship gate.
PlannedBuild 03

Roadmap scorer

Build 03 · Planned
A tool for deciding what to build nextInteractive tool / prioritization
Problem
Every request feels urgent, but the team can only do so much.Every request feels urgent and there is one team's worth of capacity.
Bet
Score each request by how much it helps for each week of work, and draw a clear line where the team runs out of time.Score each request by expected gain per engineering week and draw the capacity line in public.
Result
Planned: how many requests came in and how many the team took on. Sample requests will be labeled as samples.Planned: requests in vs commitments out. Example requests will be labeled as examples.
PlannedBuild 04

Restaurant allergen assistant

Build 04 · Planned
Safe answers to allergy questionsLLM + RAG / grounded answers
Problem
Staff answer allergy questions from menus, recipes and memory, and those don't always match.Allergen answers come from menus, recipes and memory, and those sources don't always agree.
Bet
Answer only from the restaurant's own information. If two sources disagree, say "ask the kitchen" instead of guessing.Answer only from the restaurant's own sources, and send the guest to the kitchen whenever they conflict.
Result
Planned: how often it answers correctly, and how often it says 'ask the kitchen' when it should.
PlannedBuild 05

Model router

Build 05 · Planned
Cheaper AI without worse answersLLM routing + Python / cost and quality
Problem
Using the biggest, priciest AI for every small task costs too much.Sending every request to the largest model makes each task too expensive to price.
Bet
Send easy questions to a smaller, cheaper AI and hard ones to the big one. Then use Red Pen's A test that scores how often the AI gets it right. to make sure quality didn't drop.Send easy requests to a small model, escalate hard ones, and score both with Red Pen's eval set.
Result
Planned: the cost of each task before and after, and whether the answers got any worse.Planned: cost per task before and after, and the quality difference in points.

Next up

  • Activation flowTests two sign-up flows with real users (Showing two versions to real users to see which works better.): ask people to verify first, or show them something useful first?An onboarding flow with full event tracking and an A/B test of where verification happens.
  • Weekly digestAn AI An AI that does tasks for you, not just answers questions. that reads a team's weekly numbers and writes a short note on what changed and why.An agent that reads a metrics table every week and writes the "what changed and why" note.
  • Interview synthesiserTurns customer interview notes into a ranked list of what people said most, and what matters most.Turns raw interview notes into tagged themes ranked by frequency and impact.
  • OpenAPI → Agent ToolkitLets an AI assistant use a company's existing software, without building each connection by hand.Turns an OpenAPI spec into a set of tools an AI agent can call.

I use AI to build what a team couldn't build alone, then prove it works with a realI use AI to build what a team couldn't ship alone, then prove it with an testeval, not a demo.

How I run a product. Pick a step

Frame

Write the problem on one page: who is stuck, what it costs them, and which number should change.Write the problem on one page: who is stuck, what it costs them, and which number should move.

Artifact: a one-page problem summaryone-page problem brief
Claude CodeClaude APIMCPEvalsNext.jsPythonSQLFigma

About

I've led products at Visual Comfort & Co., Zillow, Spreetail and Arcadis. Now I also build the AI myself: I put it to work in real systems, measure how well it does, and write down what went wrong.Product leader at Visual Comfort & Co., Zillow, Spreetail and Arcadis. Now I build the AI myself: ship it inside the real system, measure it, and write down what broke.

More about me
Olu Akele smiling, one hand resting on his arm
Olu Akele seated at a table, hands clasped

Proof

Selected results from my product roles
Visual Comfort & Co.Principal Product Manager · 2025–presentSource: LinkedIn ↗
  • 6 wks → 45 minvalidation and approval workflows, after leading a custom-trained LLM catalog audit agent across 1M+ SKUs and 20 teams that cleared a 150K+ SKU error backlog to zero.Checking and approving product data took six weeks. With an AI checker I led, it takes 45 minutes.
  • 15–20xmonthly SKU corrections (1,000 by hand to 15–20K) by running the audit agent in production, with human-audited accuracy up from 45% to 97%.The team now fixes 15 to 20 times more product errors each month, and the fixes are right far more often.
  • ~11xmonthly usage of an AI chatbot and MCP platform that acts for authenticated users, from ~200 conversations a week at launch to 10,000+ a month.An AI help chat I led grew from about 200 conversations a week to more than 10,000 a month.
  • 71% → 93%decision accuracy for an AI refund agent, from an eval framework built on 80 real support tickets; it launched with zero policy-cap violations.An AI that decides on refunds went from right 71% of the time to 93%, because I built a way to test it before launch.
  • $6.8Mincremental revenue from an experimentation and A/B testing framework (50+ experiments), growing paid members 29%.Testing website changes on real users before rolling them out brought in $6.8 million in extra revenue.
ZillowSenior Product Manager · 2022–2025Source: LinkedIn ↗
  • $42.2Mincremental transaction value over four quarters from multivariate tests, growing active agent adoption 31% (300.2k to 400.2k).Testing page changes with real users added $42.2 million in transactions over a year.
  • $4M+ ARRfrom AI-powered scheduling optimization for ShowingTime+, growing monthly tour volume from 740k to ~949k.Smarter scheduling for home tours brought in over $4 million a year in new revenue.
  • 3xrequests on a centralized AI service layer powering recommendations, dynamic pricing and support automation (20,000 to 60,000 a week in six months).A shared AI system I led went from 20,000 to 60,000 requests a week in six months.
SpreetailSenior Product Manager · 2021–2022Source: LinkedIn ↗
  • $400M+logistics operation across 7 distribution centers with AI-powered fulfillment; vendor onboarding cut from 8 weeks to ~5.2.I helped run shipping and warehouses for a $400-million-plus operation, and cut the time to bring on a new supplier from 8 weeks to about 5.
  • −31%monthly support tickets (15,000 to 10,350) from self-service documentation, with customer satisfaction up from 68 to 87.Better help pages meant 31% fewer support tickets, and happier customers.
  • $1.8Mdirect procurement savings from renegotiated vendor agreements ($11.2M to $9.4M).Renegotiating supplier deals saved $1.8 million.
ArcadisSenior Manager, Product Management · 2017–2021Source: LinkedIn ↗
  • −10%costs on $31M in financials managed and forecast, at 100% alignment with budget goals.I helped manage $31 million in budgets and cut costs by 10%.

Index

Builds, done and planned
  • 01ShelfReadyStore AI shoppers can readAgent-ready storefront99.3% AI-ready99.3% agent-ready / up from 78% after 105 approved fixes
  • 02Red PenSupport replies, testedEval harnessPlanned
  • 03Roadmap scorerDecide what to build nextPrioritization toolPlanned
  • 04Restaurant allergen assistantSafe allergy answersGrounded answersPlanned
  • 05Model routerCheaper AI, same qualityCost and qualityPlanned
  • NextActivation flowSign-up testOnboarding + analyticsPlanned
  • NextWeekly digestWeekly numbers noteAnalytics agentPlanned
  • NextInterview synthesiserInterview summariesResearch workflowPlanned
  • NextOpenAPI → Agent ToolkitConnect AI to softwareAgent toolingPlanned
  • EarlierWherewiseRelocation recommenderLive soon

Off the clock

Running, Sundays and a lot of patience
  • Running

    Since third grade

    I fell for running in third grade, on the track. I kept going through grade school, high school and college, then half marathons. It's not a hobby anymore; it's just how I live.

  • New York Giants

    —Days since the Giants' last Super Bowl

    Still counting. Still watching every Sunday.

  • Tottenham Hotspur

    17 years, then Bilbao

    Spurs taught me patience: 17 years between trophies, and I kept showing up. Then Bilbao: Europa League champions, May 21, 2025. Same in product: keep shipping through the hard seasons.