The AI FDE Course

Use AI is the way of working on every day. Build AI is what most days add to WorkBot.

Working with coding agents

Run Claude Code, Codex CLI and OpenCode as your development team: specs, pull requests and reviews by agents, several agents in parallel on git worktrees, then 50 at once against a backlog

Chat and voice assistants

Streaming chat on the web and in Slack, WhatsApp, SMS and iMessage; voice that listens, speaks and handles interruptions; interfaces the model composes from a catalog of components

Agents that use tools

Agents that search, read, browse and act, remember what matters, and hand off to each other; the same agent built on 3 frameworks so you can choose one

Search over company knowledge

Retrieval that explores a knowledge base, policies and manuals and answers with citations, measured against plain retrieval

Documents, images and spreadsheets

Structured data pulled out of PDFs, scans, letters, invoices and spreadsheets, with human approval where it matters

Integrations that act

The agent connected to a CRM, ticketing, a calendar and GitHub, with rules applied before the model and tools that can be dry-run and retried safely

Running on 2 providers

Anthropic and OpenAI behind one layer, routed by task, with fallbacks when one is down

Evals and production

Tests and eval suites gating every pull request, tracing and cost per customer, roles and permissions, and defences against prompt injection

Architecture and deployment

A config-first design where a new customer is configuration, queues and events, deployment to a managed platform and to a major cloud from Terraform, isolation for regulated customers, and delivery into a customer's account from a runbook

Research, growth and analytics

User research inside a deployment, a site that answer engines can cite, outreach within the rules, and an analytics stack with an agent that shows its SQL

WorkBot is an AI assistant and workflow engine for a company's operations, finance and support teams, and for the customers they serve. Employees talk to it in a web app, in Slack and by voice; customers reach it on WhatsApp, SMS and iMessage. It answers from the company's own knowledge base and policies and cites its sources, takes in work from email, documents and tickets, applies the company's rules, asks a person to approve what matters, and acts in the systems the company already runs: the CRM, ticketing and the ERP. An admin console lets each customer configure it without code, and it hands off to a person when it should.

You build it from the first day and add to it every day.

Features you build along the way, for example:

• A chat assistant that answers an employee's question from company policies and documents, and shows where the answer came from
• A support phone line that listens, speaks back and opens a ticket from the call
• An invoice read from a PDF or a photo, its fields extracted and routed for approval
• An agent that investigates a ticket: it searches past tickets and the knowledge base, checks the CRM and drafts the reply
• Approval workflows that wait for a person, survive a server restart and notify when done
• One conversation that starts on the web and continues on WhatsApp or Slack
• An admin console where a customer sets its own rules, so the next customer is onboarded with configuration alone
• Dashboards and forms the model composes from a description
• The whole system deployed into a fresh cloud account from a script, with a runbook someone else can follow
• An analytics assistant that answers business questions and shows the SQL it ran

Every day ends with features merged into WorkBot, and each day is verified from your repository before the next. 3 days are checkpoints: the midpoint design, the delivery into a customer account, and the final release.

1. Day 20
   Architecture design and product thinking

   An architecture document of 2 to 3 pages, a one-page feature proposal, and a 5-minute pitch with questions.

2. Day 37
   User research, and ship to a customer cloud

   Someone else deploys WorkBot into a fresh account from the runbook and runs the smoke evals; interview and usability findings written up with evidence and routed into configuration and the backlog.

3. Day 40
   Final release

   WorkBot live, an architecture document, a recorded 10-minute demonstration, and the numbers.

What is the AI FDE Course?

Free forward deployed engineer (FDE) training from Plank: 40 days in which an experienced full-stack engineer builds and ships one production AI product, WorkBot, the way an FDE does. It is the Plank AI Accelerator's 2-month program, open to anyone.

Who is the course for?

Engineers with 3 to 4 years of full-stack TypeScript and Node.js experience who want to move into AI engineering or a forward deployed engineer role. No prior AI engineering experience is required.

How long does the FDE training take?

40 days of work, in 8 weeks or faster. Week 1 sets up the AI-powered development workflow; weeks 2 to 8 build WorkBot through chat, agents, retrieval, voice, evals, integrations, security, infrastructure and a final release.

Is the course free?

Yes. The days, walkthroughs, verification and profile are free. You pay for your own model and cloud usage.

How is each day verified?

Sign in with GitHub and link a public repository. When you finish a day, push and verify: the commits since your last verified day are checked against what that day ships, and the day is recorded with its commit.

What do I have when I finish?

WorkBot deployed, and a public profile on joinplank.com, under your GitHub login, listing every verified day, its commit and the skills it covers. Plank hires forward deployed engineers, and a verified profile is a record of shipped work you can link in an application.

How does the course relate to the Plank AI Accelerator?

The course is the Accelerator's 2-month program, open to anyone and done at your own pace. The full Accelerator is a selective one-year program, run in person, that ends with a role at Plank as a forward deployed engineer.