Viewing profile — tiny-automates

fetch : https://www.tinyfish.ai/blog/production-grade-web-fetching-f...

hey hn, we've been building the web infrastructure for ai agents at tinyfish. our agent primitive was already out. just went live with 3 new primitives - search, fetch, and browser…

thanks! glad the visuals helped, we wanted the data to speak for itself.

yeah that's basically the whole thesis compressed into six words. we kept trying to articulate why the CLI worked better and it always came back to that - MCP does discovery really…

the finding that buried everyone: moving "allow yourself to be shut down" from the user prompt to the system prompt made models sabotage more often, not less. Grok 4 went from 93% …

been thinking about this a lot lately. the original idea is simple : luck = doing × telling. but after 10 years of actively running this playbook, i think the model undersells what…

i'm building TinyFish ( https://tinyfish.ai )- browser automation APIs built for AI agents. most agent frameworks treat the browser like a human would (screenshot, click, pray), wh…

agreed, and i'd go further - the harness is where evaluation actually happens, not in some separate benchmark suite. rhe model doesn't know if it succeeded at a web task. the harne…

the harness being "9 lines of code" is deceptive in the same way a web server is "just accept connections and serve files." the hard part isn't the loop itself — it's everything ar…

the planner-executor isolation point is what stood out to me. right now most browser agent frameworks treat the LLM as both the decision-maker and the one processing untrusted cont…

[flagged]

agree that this is a protocol-level issue, not framework-specific. but the "all external tool calls require confirmation prompts" mitigation doesn't really apply here - the exfil h…

the unfurling vector is elegant because it exploits a feature that predates LLMs entirely, link previews were designed for human-shared URLs where the sender is trusted. once an LL…

that's the user-facing definition but the implementation distinction matters more. "takes longer than you're willing to wait" describes the UX, not the architecture. the engineerin…

"background job" is actually the more honest framing. the interesting design question you're pointing at, what happens when it wants attention, is where the real complexity lives. …

frontend QA is exactly where i've seen the biggest ROI with browser agents. the gap with Playwright MCP specifically is that it assumes the agent can reason about CSS selectors and…

the abstraction level argument is spot on. i've been working on browser automation for AI agents and the biggest lesson has been that exposing Playwright-level primitives to a foun…

i go back and forth on this. when i'm working on something where the hard part is the actual algorithm, say custom scheduling logic or a non-trivial state machine, i need my hands …

i've been building agent tooling for a while and this is the question i keep coming back to. the actual failure mode isn't messy code, agents produce reasonably clean, well-typed o…