Archive / Automation & agents
A 1960 paper argued computers should share decisions with people
Licklider's Man-Computer Symbiosis proposes cooperative decision-making, not machines resembling language models.
3 min readAutomation & agents
Make the failure path part of the workflow
An automation needs more than a happy-path demonstration. Give each event an identity, contain retries, make approval meaningful and test changes before widening the scope.
Your working sequence
- Prevent duplicate records before an automation goes live
Stop retries, webhook repeats, and double clicks from creating duplicate business records or actions.
- Separate retryable failures from work that needs a person
Keep an automation from hammering a failing service or losing records that cannot complete automatically.
- Design approval gates that reviewers can actually use
Add human review to a consequential workflow without creating blind approvals or permanently stuck runs.
- Release an automation change like a small software change
Change a live automation without discovering mapping or logic errors across the entire workload at once.
Go back to the underlying research
Read the original chapter with its caveats. Or use the work tools to make the next decision explicit.
From the archive
All topic recordsArchive / Automation & agents
A 1966 paper warned about its own illusion of understanding
Weizenbaum's ELIZA paper explains the pattern-matching script and flags how readily users assumed it understood them.
3 min readArchive / Automation & agents
OpenAI's first browser agent paused itself before purchases
OpenAI's own announcement and safety card show why Operator asked a human to confirm before finishing consequential actions.
3 min readArchive / Automation & agents
Anthropic called its own screen-controlling model error-prone
Anthropic's launch post and tool documentation both name specific computer-use failure modes rather than smoothing over them.
3 min readArchive / Automation & agents
ChatGPT's agent mode still asks before it spends money
OpenAI's launch post and its connector-permissions documentation describe where agent mode pauses for a person and where it does not.
3 min readArchive / Automation & agents
Make added a step that picks its own next move
Make's own documentation distinguishes an AI-agent module from a fixed scenario step and names what still needs a human check.
3 min read