Ikenna Nwakwesi
Portfolio / 2026 / TorontoToronto Work with me

Product · Partner ecosystems · AI systems

Enterprise experience.
Practical AI systems.

I bring 10+ years in product management, partner ecosystems and commercial operations to building tools for the work I know.

I define the architecture, direct AI-assisted implementation, and personally test and validate the result. The work below shows the systems, the decisions and the evidence behind them.

i. Define the architectureii. Direct the buildiii. Test & validate

Featured / 2026Move across to browse

Index / Case studies

Featured

Case Studies & Builds

Bespoke

Reading, voice and desktop actions

Operator-controlled reading, voice interaction and desktop actions — a local tool for moving between the written word, conversation and repeatable steps.

The operator stays in control of each mode: speaking text, asking a turn, a live conversation, or replaying a verified desktop step against a durable target. Replay follows the operator’s selected approval mode.

Baton hand-offs run as a Bespoke surface: routing and coordination between agents, so work can move through the wider environment without a separate case study here.

Public demo + source

DIA

Discovery Intake Agent

A questionnaire becomes a scored opportunity and three useful documents.

A deterministic pipeline handles parsing, validation, scoring and document generation. A Gemini agent uses those functions as tools.

I brought together the workflow, interface, document generation, testing and deployment for the Google for Startups AI Agents Challenge.

Design decisions & what to inspect

The deterministic path makes the scoring and generated documents inspectable without relying on a model response. The agent can call the same functions rather than invent a separate scoring process.

The public repository includes parser and scoring logic, fixtures, tests and an evaluation harness. See the dated build record ↓

Blackboard

A visible record of work across people and agents.

A local viewer for file-based events: handoffs, shared artifacts and activity across the fleet. I use it in my own environment and refine it through practice.

The implementation choice

The record remains readable even when the viewer is down.

Events are plain JSON files.

The build record

A few dated implementation steps.

2026Scroll to browse

  1. 06–09 Jun 2026DIAFrom public demo to capture tooling
  2. 27–28 Jul 2026Amazon AdsA queryable reporting pipeline
  3. 08 Oct 2026BespokeRepeatable desktop actions
  4. 09 Oct–17 Nov 2026BespokeMini-cursor chat, native capture and the Navy companion
  5. 09 Oct–18 Nov 2026BASH siteServices, clay launch, booking routes and intake
  6. 10 Oct–13 Nov 2026Supporting systemsThe smaller repos the main work runs on
  7. 11 Oct–15 Nov 2026TiaOutput canvas, gated exports and workspace rebuild
  8. 16–23 Oct 2026Family TreeNwakwesi family record
  9. 23 Oct 2026DIAPersona v1.2 and the Savant scoring build
  10. 23 Oct–15 Nov 2026This siteThe business card and the November redesign
  11. 23 Oct–17 Nov 2026ComponentsIcons, prototypes and reference sections
  12. 16–17 Nov 2026Navy’s Petting ZooThe cast, their reactions, and a day/night world

Tools I work with

Bespoke

Operator-controlled reading, voice interaction and desktop actions. A local tool for moving between the written word, conversation and repeatable steps.

speak
Read text with playback controls.
ask
Answer a prompt, then speak the response.
live
Stream microphone audio and native audio replies, with interruption handling.
cursor
Desktop actions with durable targets and verified step recipes.

Baton

Routing and coordination between agents, supporting how work moves through the wider environment.

Agent Eggs

Portable context and capabilities, packaged so useful knowledge can travel between environments.

Reusable context packages

Research & writing

dPKL is the foundation of how I think about AI systems. These four connected works explore knowledge, execution, the operator’s role and human autonomy.

Main framework · v1.1 · 29 July 2026

The Deterministic Personal Knowledge Layer (dPKL): Agents as the Interface to Deep Execution

A local-first approach to making working knowledge portable and queryable, with agents acting as an interface to execution.

  1. What Expectations? AI, Telecommunications, and the Tool It Always Was

    Essay · v1.1 · 29 July 2026

    AI as infrastructure and a tool, with human judgment shaping how its capabilities are used.

  2. Agents Are Your New Mouse and Keyboard: An Operator’s Doctrine for Driving Agents

    Operator doctrine · v0.5 · 3 August 2026

    An operating practice for directing agents through command-line tools, documentation, reusable capabilities and human validation.

  3. What Autonomy Is, and Why It Remains Exclusive to Humans

    Draft essay · v0.1 · 6 August 2026

    A philosophical argument for keeping purpose and responsibility with humans, and designing agents for bounded, reliable execution.

The ideas and operational experience are mine.

Where the judgment comes from

Product lines, partner programs and commercial operations taught me to account for the messy parts: incomplete information, handoffs and competing priorities.

LG ElectronicsCommercial operations & retail media
TD SYNNEXProduct lines & vendor relationships
Ingram MicroMicrosoft Surface partner programs

That experience shapes the problems I choose, the systems I design and what I check before calling something useful.

Put a workflow to work.

Have a recurring workflow that needs attention? I work on business automation through BASH. Start with one task, agree to the scope and acceptance checks, and then build from there.

Bash Systems rates, CAD/hr: Consultation $75 · Project $155 · Advanced technical $215.

Credentials

  • Build a Secure Google Cloud Network Skill Badge
  • Build Infrastructure with Terraform on Google Cloud Skill Badge
  • Develop Your Google Cloud Network Skill Badge
  • Implement Cloud Security Fundamentals on Google Cloud Skill Badge
  • Set Up an App Dev Environment on Google Cloud Skill Badge
  • Implement Load Balancing on Compute Engine Skill Badge
  • Create Your First Gemini Enterprise Application
  • Engineer AI Agents with Agent Development Kit (ADK)

Interactive business card: drag, throw or poke it

Loading business card…