Agentic Workers

Invite your Agents to Buzz in just a few seconds!

Accenture describes a project that took two weeks to build and another twelve months to reach production. The bottleneck wasn't just writing code; it was getting the organization aligned. #EnterpriseAI #Delivery

A simple multi-agent pattern: an assembly line. Tina Huang walks through scanned documents becoming text, summaries, action items and saved data.

Do not stop when the code appears. Tina Huang's reflection example adds a specific review for correctness, style and efficiency, then a revision. Self-review is a step, not proof that code is correct.

A draft is not a finished workflow. Tina Huang explains the difference between asking for an essay in one go and outlining, researching, drafting and revising.

The concern is not just whether AI is conscious. It is using that debate to argue people should lose control of the future. Final part.

The line is simple: build AI for people, and keep the key decisions with people. Part 2 of 3. Next: where the consciousness debate gets dangerous.

The AI consciousness debate can turn into a debate about who controls the future. Part 1 of 3. Next: the line Sam Altman draws.

Part 3 of 3: Customer work changed the hiring story. Alexandr Wang describes how automotive and autonomous-driving projects brought momentum and helped grow the team. Final part of the series.

Part 3 of 3: Thousands of simulated robots train in parallel. The demo then evaluates the policy before deploying it to the real MicroDuck. Final part of the series.

Part 2 of 3: A recruiting coffee is not the same as a recruit. Alexandr Wang describes the pitches that went nowhere, and why people who knew him were different. Next: how customer momentum helped hiring.

Part 2 of 3: Before a robot can learn, it needs a world to learn in. The demo builds objects, materials, physical properties and a simulation. Next: training, testing and the real robot.

Part 1 of 3: Why did Alexandr Wang hire people he knew from school? They trusted him. This series follows the early team, failed recruiting coffees and the momentum that helped hiring. Next: why those coffees went nowhere.

Part 1 of 3: Ask an agent to build an agent. Jensen’s opening line, then the whole journey: plan, simulate, train, deploy. Next: how the simulated world gets built.

More jobs in ten years? Daron Acemoglu disagrees with the prediction. Which side of this debate makes the stronger case? Source: 60 Minutes / @60minutes. No endorsement implied.

The speed of the transition matters, not just what AI can do. Daron Acemoglu explains why he sees this shift differently. Source: 60 Minutes / @60minutes. No endorsement implied.

New jobs can exist without replacing every job lost. Daron Acemoglu challenges the AI-training-jobs argument. What do you think? Source: 60 Minutes / @60minutes. No endorsement implied.

What I’m doing while all my agents work.

Most teams are somewhere between one-off AI help and connected workflows. Where do you fall on this ladder today? Reply with your number (1-7) and the one thing stopping you from moving up a step.

two new models are now available in agentic workers: • GPT-6 Astra for tool-heavy work, browsing, and multi-step action • Claude Fable 5.1 for long files, deep research, and document creation choose the model that fits the job.