Redact PII before your model searches the web
Build a loop where Rampart redacts personal details on your machine, Tabstack researches the redacted question, and your own model writes the reply. Four short Python files.
Tabstack Blog13 min read
Tabstack
32 stories
The production-readiness checklist for current-answer features
Use seven release gates to check a current-answer feature. Define acceptable answers, test failures, and attach the evidence your team needs to ship.
Tabstack Blog7 min readThe 22-line demo and everything it was missing
I asked a 22-line Tabstack Research demo what had changed in the latest Laravel release, and it told me 12.x. Oops. Here's how I took it to production one commit at a time: routing, deadlines, retries, caching, and checking the answers against the changelog.
Tabstack Blog22 min readBuild a 20-question evaluation set for a live-web feature
Define expected answer elements, freeze source evidence, and review a live-web feature with a small evaluation set that keeps failures and missing scores visible.
Tabstack Blog7 min readWhen should you use search, agentic search, a Research API, or build the loop yourself?
Compare search APIs, agentic search, Research APIs, and DIY loops. Choose by required output, control, data boundaries, and operational ownership.
Tabstack Blog9 min readWhat "private by default" means for a managed web API
What a Research call sends, who processes it, what we retain afterward, and the detailed data collection setting that controls it.
Tabstack Blog3 min readTrace a question from request to source-backed answer
Record a Tabstack Research request, preserve its cited pages, and check the answer against its sources with a Python review sheet.
Tabstack Blog10 min readWhat makes a citation useful in an AI-generated answer?
How to check whether citations in an AI answer support its material claims, scope, and date.
Tabstack Blog6 min readWhere model-operated web research breaks
Nine places web research fails after search has already succeeded, each with a signature you can observe, the evidence that identifies it, and the smallest test that catches it.
Tabstack Blog11 min readAdd current, cited answers to your model application without touching the model
A second path at the application layer sends current questions to a managed Research call and returns a cited result in your own response shape, with the model left exactly as it is.
Tabstack Blog8 min readThe seven stages of web research for a model you run
A web research system you can trust with a current question does seven separate jobs. It defines what a complete answer looks like, discovers candidate sources, retrieves them, extracts evidence, checks that evidence for gaps, reconciles conflicts, and writes a cited result.
Tabstack Blog12 min readSearch + fetch + model versus a managed Research call: the evaluation plan
We are comparing two complete ways of answering current public-web questions: a pinned search + fetch + model pipeline the application runs itself, and a single managed Research call. This article publishes the pre-registered method. It does not publish a winner.
Tabstack Blog9 min readBuild a cited live-web answer in Python with one Research call
Clone the example, set one environment variable, and run one command to send a current question to Tabstack Research. The call streams progress, then writes a Markdown report and a machine-readable list of cited pages.
Tabstack Blog8 min readSearch gives your model sources. What turns them into a cited answer?
A web search API can return useful titles, URLs, and excerpts. A cited answer requires a research loop after search: define the question, select and read sources, identify gaps, reconcile evidence, write the answer, and preserve the claim-to-source connection.
Tabstack Blog12 min readGive a LlamaIndex.TS agent live web access
Install @tabstack/llamaindex, pass the tools to an agent, and let it read pages, pull typed fields, and research questions across sources on demand.
Tabstack Blog6 min readAdd web tools to an OpenAI Agents SDK agent with Tabstack
A step by step tutorial: install @tabstack/openai-agents, hand the tools to an Agent, and understand why the adapter registers them with strict mode off.
Tabstack Blog6 min readGive a Claude Agent SDK app web access
Install @tabstack/claude-agent, wire its ready-built in-process MCP server into a query() call, and give Claude extraction, research, and browser tools.
Tabstack Blog7 min readBuild a web-connected Mastra agent with Tabstack
A step by step tutorial: install @tabstack/mastra, spread the tools into an Agent, and give it schema-enforced extraction, research, and browser automation.
Tabstack Blog6 min read
Showing 18 of 32 stories
Load more storiesAiByts Weekly Brief
Get the top AI news and tools straight to your inbox every week.
Weekly · AI news
Join 15,000+ AI enthusiasts