Blog · Topic
Tutorials
Step-by-step builds: a pipeline, script or workflow you can copy, run and adapt to your own prompt set.
Articles
API errors and retries: a policy that never double-charges
Which errors to retry, which to fix, and which are final: 429s, 5xx, timeouts and batch item errors, with retry wrappers in Python and TypeScript.
MCP setup for Cursor and Claude Code: ask AI engines
Connect Cursor or Claude Code to the hosted MCP server so the editor can query ChatGPT, Gemini, Copilot, Google and Google AI Mode as tools, with costs and key safety.
Idempotency keys explained: safe retries for async tasks
How idempotencyKey prevents duplicate tasks and double charges: key design, 409 handling, crash-safe batch resubmission, and what keys do not dedupe.
Give a LangChain agent live AI answers as a tool
Turn ChatGPT, Gemini and Google News into LangChain tools so an agent checks live answers mid-reasoning. JavaScript and Python setup, plus guardrails.
Run your own AI citation study: a defensible methodology
Measure citation rates, trigger rates and source mixes in AI answers yourself: study design, sample sizes, intervals, code and a reporting checklist.
Verify webhook signatures: HMAC-SHA256 in Python, Node, Go
Verify a webhook's HMAC-SHA256 signature on the raw body, check the timestamp, handle secret rotation. Tested code for Flask, FastAPI, Express and Go.
Webhook receiver design: retries, duplicates and ordering
Build a webhook receiver that loses nothing: verify, write to an inbox, ack fast, dedupe by task.id, handle retries and out-of-order results, reconcile.
AI-answer alerts without code: a Zapier setup
Post a Slack alert and log a sheet row when an AI answer stops (or starts) naming your brand or citing your domain, built in Zapier with no backend.
Bing Search API alternatives after its 2025 retirement
Microsoft retired the Bing Search APIs on August 11, 2025. What it recommends instead, verified alternatives and prices, and a parameter migration map.
ChatGPT visibility tracker: metrics, prompts and sampling
Choosing a ChatGPT visibility tracker: what the platforms report, what building your own takes, and the metrics and sampling either option must get right.
Content theft detection with exact-match search queries
Find sites that copied your articles: pick fingerprint sentences, run quoted Google queries that exclude your domain, score candidates, and file removals.
GEO checklist: 24 items, each with a check you can run
A generative engine optimization checklist where every item has a pass/fail test: crawler access, snippets, content, off-site presence and measurement.
How to get Google AI Mode answers as JSON
Send one prompt to Google's conversational answer surface and store what comes back: answer text, sources, citation pills, products, places and videos.
Google AI Overview API: get AI Overviews as JSON in 2026
Which APIs return Google AI Overview content, how each is requested, the JSON fields and what it costs, with verified vendor prices and working requests.
Google Alerts API: there isn't one. What to build instead
Google offers no Google Alerts API. The options for programmatic alerts, and a pipeline built on scheduled news and search tasks with signed webhooks.
Google Custom Search JSON API alternatives and migration
The Custom Search JSON API is closed to new customers and existing ones must move by January 1, 2027. Options, verified prices and parameter mapping code.
Google dorking for defenders: find what your site exposes
Defensive search operator queries to find exposed files, staging hosts and error pages on domains you own, run them on a schedule and remove what leaks.
Google search operators that still work in 2026
Which Google search operators Google documents, which are undocumented, and how to run site:, quotes, filetype: and before:/after: queries at scale.
Google search parameters: gl, hl, uule, num and more
What each Google search URL parameter does, how it maps to this API's request fields, which combinations return 400, and what each request costs.
Monitor Microsoft Copilot answers with an API
Get Copilot answers and the sources they cite as JSON, per country, sync or in async batches; search queries, shopping cards and map results are coming.
Monitor Google Gemini answers with an API: fields and code
Get Gemini answers, sources, citation pills and place cards as JSON, with curl, Python and TypeScript examples and credit costs.
Monitor Grok answers with an API: X posts and sources
Get Grok answers as JSON: text, sources with X post metadata, search queries and model, per country. Code, field guide and credit costs.
Online reputation monitoring for search, news and AI
Monitor what Google, its AI Overview, news and AI assistants show about your brand: query set, schedule, snapshot diffs, alert rules and human review.
Turn Google results into typed data, not HTML scraping
One Google Search call returns organic results, ads, People Also Ask, local pack, knowledge panel and AI Overview as typed JSON, targeted by country per request.
How to get Google News results as structured JSON
Request news results per country and language, read every field on an article record, and build brand alerts and coverage reports on top of them.
Monitor Perplexity answers with an API: citations and media
Get Perplexity answers as JSON: sources, citation pills, related and search queries, media, places and shopping cards. Python, TypeScript and credit costs.
Scheduled AI-answer monitoring in n8n: a complete workflow
Build a daily AI-visibility check in n8n: schedule prompts, queue async tasks, receive results by webhook and write mention and citation rows to a table.
Rank-tracking pipeline for AI answers with async batches
Build a citation rank tracker in Python: batch submission that is safe to re-run, signed webhook collection, a reconciliation pass, and the rank rows.
Track Google AI Overviews at scale with async batches
Submit a keyword list as GOOGLE task batches with AI Overviews requested, collect signed webhook deliveries, and store citations you can trend over time.