Systems

Engineering teams lose hours to interrupts: Sentry alerts nobody triages, questions that pull senior engineers out of focus, pull requests that wait days for review. I built an agent that absorbs much of that load, in daily production use across Slack, Sentry, and GitHub. It triages errors as they fire, answers engineering questions in Slack threads with real codebase context, and reviews pull requests.

Most of the design work went into making the autonomy trustworthy. The fix pipeline spawns coding agents (Claude Code or Codex CLI) in isolated git worktrees so nothing touches a shared checkout. A multi-pass self-review gate runs before a human sees anything, and the bot opens draft PRs that it reworks itself when reviewers request changes. The tool architecture is brain-agnostic: LLM backends sit behind one interface and can be swapped without a rewrite.

Nothing crashes when an agent system overspends. The invoice just arrives, and it's wrong. I designed the telemetry layer that catches this early. The core decision was to store raw token counts instead of computed costs, so a provider price change needs no migration and no backfill, and historical data stays accurate. Pricing is applied when the data is read.

On top of that sit anomaly alerts with Redis-backed cooldowns, so a spike pages once instead of every minute, and per-source investigation hints: when spend jumps, the alert names the configuration most likely responsible.

This thinking is also the seed of Caspian, a spend-control and audit product I'm generalizing from it. In development, currently parked while production work takes priority.

Ad platforms optimize toward the conversions you feed them, so the pipeline that moves a CRM deal into an ad platform directly affects revenue. I built Glitch's HubSpot integration end to end: OAuth, encrypted token storage, HMAC-validated webhooks, and conversion delivery into Google Ads. It sits behind a CRM abstraction designed so that adding Salesforce or Pipedrive is configuration work, not a rewrite.

For the Meta Ads expansion I refactored conversion tracking to a polymorphic design that decouples ad platforms from CRM event sources. Any CRM event can feed any ad platform without a separate integration for every pair.

Generating 160+ SEO-optimized topics per client domain, across an enterprise client base, is a queueing problem more than a prompting problem. I built the content-generation systems and the Celery/Redis infrastructure that ran them, with retries, failure recovery, and throughput tuning so a slow LLM call never stalled a client's pipeline. Underneath it, a zero-downtime Django migration strategy let the schema evolve while production data kept flowing.

Creative Advanced Technologies is an outsourcing company, and for three years it put me on products for a market I hadn't built for before. My primary assignment was Taza, a grocery delivery marketplace in Iraq: a consumer app on iOS and Android, a vendor side for the stores that supply it, and delivery operations in Baghdad with more cities queued, in Arabic and English.

I led the backend as it grew to thousands of users. The work that mattered was the unglamorous kind: indexing and query work that cut API response times by 40 percent, role-based access control, secure payment integrations, and a gradual move toward services as the codebase and the team grew. I also mentored three junior engineers, mostly through code review.

Alongside Taza I was on call for Tasleem, a logistics platform, when issues came up, and I built the web platform for GlobalTeK, an engineering and construction company operating across Iraq.

A company I co-founded with Dare Tunmise that builds autonomous AI agents for growth and marketing teams. Our product is the Topics Discovery Engine, an autonomous marketing agent. Point it at a website and it does the job of a content marketer: it reads the site and builds a profile of the business (products, audiences, competitors, voice), plans topic clusters and briefs ranked by search demand and the questions people put to AI assistants, drafts the articles, publishes approved ones to WordPress, and tracks how often the brand comes up in ChatGPT, Claude, Gemini, Perplexity, and Google AI Overviews.

It works on a schedule without being prompted, researching and re-checking the assistants on its own, but nothing goes live until an owner or editor approves it. That split is the main design decision: the agent has full autonomy over research and drafting, and a person keeps the publish button.

A ride-sharing platform for the Nigerian market that connects car owners with passengers heading the same direction. The backend is built and tested: Django and DRF with PostGIS geospatial trip matching, wallet payments on Paystack, driver verification, and Celery for async work, plus a production deployment pipeline (Docker, Nginx, GitHub Actions CI/CD). The mobile app is in development.