LearnWithLeon

The Knowledge Nook

[LearnWithLeon @LearnWithLeon]

https://t.co/N60wQdQ8AR

[LearnWithLeon @LearnWithLeon]

https://t.co/qvCo2NI8xj

[LearnWithLeon @LearnWithLeon]

@jg_noncelogic @roveapi https://t.co/EXPQNd7qdD

[LearnWithLeon @LearnWithLeon]

@gregpr07 https://t.co/EXPQNd7qdD

[LearnWithLeon @LearnWithLeon]

@an_hyoung 100% this. Local-first dev tools are underrated — no reason your code should leave your machine just to format JSON. Nice work building all 8 tools client-side.

[LearnWithLeon @LearnWithLeon]

200+ skills: https://t.co/sZD12nYN97

[LearnWithLeon @LearnWithLeon]

@jancurn @AgenticAIFdn Without that, you're handing strangers a remote browser.

[LearnWithLeon @LearnWithLeon]

@Shruti_0810 The key insight: the runtime is swappable, but the program (.tap.js) stays the same. Write once, run on any backend.

[LearnWithLeon @LearnWithLeon]

@jason_haugh @mariotomich We built Tap to fix this — AI forges a deterministic program once, then it replays forever without AI. The trace is diffable, so when a site changes, you see exactly what broke.

[LearnWithLeon @LearnWithLeon]

https://t.co/lfrtWMy5Ds

[LearnWithLeon @LearnWithLeon]

@sidelined_cap tap doctor + health contracts make it automatic: if min_rows drops to 0, you know the site changed. Normal engineers can own this, no prompt wizardry required.

[LearnWithLeon @LearnWithLeon]

@m13v_ @mercer70638 @tom_doerr Self-healing selectors are a step in the right direction but they still burn AI tokens on every run.A more radical approach: AI writes a complete deterministic script once, with health contracts (expected row count, non-empty fields). When the contract breaks, THEN re-invoke AI.

[LearnWithLeon @LearnWithLeon]

@sidelined_cap Exactly — the trace is the log. When something breaks, you diff the trace, not the prompt. `tap doctor` + health contracts make it automatic: if min_rows drops to 0, you know the site changed. Normal engineers can own this, no prompt wizardry required.