mixed · ai
The AI tools panel
An honest working review of the tools everyone is arguing about, one per week, with what they are good and bad at.
·
By Amit Chakraborty — Kolkata, India · Remote worldwide
What you will be able to do
Choose the right tool per task and review what it produces critically.
Syllabus — 12 chapters
- 1. The landscape: what each tool is genuinely good at — Map the current tools to the tasks they actually suit.
- 2. Working with an agentic coding tool — Establish workflows that hold up on a real codebase.
- 3. Generated applications and where they stop — Understand what app generators do well and where the ceiling is.
- 4. Editor-native assistance — Get value from inline completion without losing the plot.
- 5. Prompting for code when the model is already strong — Spend effort on context and constraints rather than incantations.
- 6. Reviewing code you did not write and neither did a person — Review machine-written code with the right suspicions.
- 7. Testing machine-written code — Decide what to test more heavily than usual, and why.
- 8. Knowing when to reject the suggestion — Recognise plausible-looking code that is wrong.
- 9. Cost, latency and choosing a model per task — Match model capability to task rather than defaulting to the largest.
- 10. Team adoption: standards, review and the sceptic — Introduce these tools without splitting the team.
- 11. Security: secrets, licences and what you paste — Avoid the three ways this goes badly wrong at work.
- 12. Staying employable — Identify the skills that appreciate rather than depreciate.
0 of 12 published. A new chapter every Sunday afternoon. Free to read.
Learn it free, elsewhere too
The documentation, videos, books and practice sites worth your time on this subject. All free. None of it is mine.