Lessons
Six lessons, drawn first from accounts written since June 2026. Each one names the accounts it rests on, so you can read the evidence for yourself.
Choose a question worth answering
Before asking an agent to tackle a research problem, ask who would care about the answer and what it would tell them. Revisit those questions when the first results come in. A calculation can become feasible long after specialists know what answer to expect.
Read the lesson and its examplesRests on
- Using physics tools to study a forestMatthew Schwartz, physics, 1 Oct 2026
- Exploring a question in knot theoryRobert Lipshitz, mathematics, 27 Oct 2026
Build the method and its checks together
An agent can help build the tools a research method needs. Decide while building how you will tell whether the method works. For a new search, compare what it returns with existing searches. For a simulation you want to repeat, review the setup before reusing it on new inputs.
Read the lesson and its examplesRests on
- Aaron Taylibrary science, 24 Jun 2026
- Ke Xiao, Han Li, Teng Zhang, Yangchen Xu, Runze Mao, Zhi X. Chenengineering, 15 Jul 2026
- Joshua Sternfeldhistory, 20 Apr 2026
Use a council of models
When I have a decision that matters, I give several models the same question and brief and ask them to answer separately. I compare their reasons, especially where they disagree, before deciding what to do.
Read the lesson and its examplesRests on
- Chris Blattmaneconomics, Oct 2026
- John H Boyerphilosophy, 20 Nov 2026
- Matthew Schwartzphysics, 23 Mar 2026
- Tiago Venturapolitical science, 2026
Start with a known result and keep an independent check
Try the method first on a result you already know. Before moving on to new work, decide how you will check an answer when there is no published result to compare it with. Where possible, make that check independent of the code that produces the answer.
Read the lesson and its examplesRests on
- Using physics tools to study a forestMatthew Schwartz, physics, 1 Oct 2026
- Terence Taomathematics, 13 Aug 2026
- Checking an R port against StataFrancis DiTraglia, economics, 21 Jul 2026
Keep enough of the work to resume, audit and undo it
Keep the original material, the last usable output and a record of what failed. If a long run stops or a correction goes wrong, you need to know what you can reuse and what you have to do again. A saved decision can also keep a new session from repeating a failed approach.
Read the lesson and its examplesRests on
- Tracing summaries to a radio archiveDominik Lukeš, digital archiving, 24 Oct 2026
- Terence Taomathematics, 13 Aug 2026
- Chris Blattmaneconomics, Oct 2026
- Thomas D. Grantlaw, 20 Nov 2026
- John H Boyerphilosophy, 20 Nov 2026
Routine research work is a useful place to start
Try an agent on a recurring task whose output you can check against the project files, such as preparing for a meeting from past notes or flagging inconsistencies in a manuscript. A task you do often gives you a reason to spend time explaining it and a chance to see whether the next attempt takes less work to check.
Read the lesson and its examplesRests on
- Chris Blattmaneconomics, Oct 2026
- Robert Lipshitzmathematics, Jul 2026