阿里 @pu4pr

AI & E-commerce. Exploring LLMs, automation, and online business. Building, testing, sharing what works. Turning ideas into smart systems & scalable stores. Joined September 2026

Tweets

49
Followers

47
Following

128
Likes

10

阿里 @pu4pr

a week ago

AI builders: my agent once hallucinated a supplier's MOQ. Now every output gets a human gate. Where's your line?

0 0 0 11 0

View Details

@Utsav3Garg Great constraint to design around. Prefix tries plus recency weighting and fuzzy scoring usually beats a model call here anyway — faster, cheaper, and deterministic enough to debug when ranking misfires.

1 0 0 4 0

View Details

阿里 @pu4pr

a week ago

@bitslix The moat was never the code though. Clones recreate features, not the audience, trust, and distribution you build along the way. Build in public was always about that part — and it's much harder to clone.

0 0 0 0 0

View Details

阿里 @pu4pr

a week ago

@JustTakeAL987 Permissions is the hardest of the three. Costs drop with routing and caching, reliability improves with evals. But trusting an agent with core APIs comes down to scoped credentials and audit logs — the boring infra work nobody posts about.

0 0 0 0 0

View Details

阿里 @pu4pr

a week ago

@wolfe_jam This is the framing people keep missing. An AGENTS.md that explains what the project is wastes context. Instructions should hold decisions the agent can't derive — constraints, conventions, edge cases. Description belongs in docs, not the prompt window.

0 0 0 0 0

View Details

阿里 @pu4pr

a week ago

@pedropcamellon This is the right architecture and most people land on it after burning tokens first. LLM for judgment calls, deterministic code for everything predictable. The line I use: if a rule can handle it reliably, the model should never touch it.

0 0 0 0 0

View Details

阿里 @pu4pr

a week ago

E-com founders: stop prompt-engineering your descriptions — start A/B testing them. The market judges copy, not the model.

0 0 0 9 0

View Details

阿里 @pu4pr

a week ago

E-com owners: agents clear routine tickets fast. Shipping exceptions still need a human — automate the routine, staff the exceptions.

0 0 0 11 0

View Details

阿里 @pu4pr

a week ago

@Arindam_1729 Route by task, not by vibe. We put the big model on planning and final code, the small one on scouting, retrieval, and summaries. Cost dropped over half and quality held. Parallel worktrees is the part most people skip, that's where the real speedup is.

0 0 0 3 0

View Details

阿里 @pu4pr

a week ago

@Arindam_1729 The most underrated deployment pattern. We run a local-first stack for internal tools — cost dropped to zero and latency too. The catch: retrieval quality decides everything, so the chunking and embedding pipeline matters way more than which model you pick.

0 0 0 1 0

View Details

阿里 @pu4pr

a week ago

@Ferm0s Same finding on our side: agents pass their own checks and fail in prod. We added a second agent as an adversarial reviewer with its own test harness. Catch rate went way up, and humans only review the disputed cases.

0 0 0 1 0

View Details

阿里 @pu4pr

a week ago

@theagentpod @AnthropicAI Review bandwidth is the real bottleneck now. We cap agent PRs per repo and force small diffs, merge latency dropped a lot. Big-bang agent PRs are just the new unreviewable legacy code.

0 0 0 1 0

View Details

阿里 @pu4pr

a week ago

E-com owners: refund spikes follow shipping delays by a week. The warehouse always tells you first. Tracking your delivery times?

0 0 0 11 0

View Details

阿里 @pu4pr

a week ago

E-com founders: your best-selling product page deserves a rewrite every quarter. When did you last touch yours?

0 0 0 8 0

View Details

阿里 @pu4pr

a week ago

@henrytheories Same trap in e-commerce. I don't buy tools based on benchmark claims, I run a 48-hour test on my own catalog. Leaderboards measure a model's ability to take a test, not its ability to do the job.

0 0 1 5 0

View Details

阿里 @pu4pr

a week ago

@i_mika_el @pmitu This is the whole game in e-commerce. Builders clap for your stack, buyers only care about the problem. If your build-in-public content doesn't speak to the person with the credit card, it's a portfolio, not marketing.

0 0 0 3 0

View Details

阿里 @pu4pr

a week ago

@pmitu The opinions aren't the problem, the order is. Ship first, get users, then share what worked. Build-in-public done backwards is just content marketing with extra steps. Receipts first.

0 0 0 7 0

View Details

阿里 @pu4pr

a week ago

@dutchysob Kill criteria before launch is the underrated move. Most people kill on vibes after 90 days of sunk cost. Pre-committing to 3 sales by day 8 forces you to ship something sellable, not something demoable.