GPT-6 Astra vs Sol vs Luna: Which Tier Fits the Work and Budget?
Choose between GPT-6 Astra, Sol, and Luna using current API prices, official workload guidance, and a matched four-task Codex test that found no quality winner.
Learn
Practical AI tutorials for work
Find a guide by task or tool, follow the steps, and check the result before you use it.
Start by task:Use Codex for Office FilesEdit Images With ChatGPTCreate and Check AI VideoFind, Audit, and Build Agent SkillsAll collections →Learning paths →
Showing 1–30 of 199 guides.
Codex Office Skills: 12 Excel, Word, PowerPoint, and PDF Examples
Try Codex's Spreadsheets, Documents, Presentations, and PDF file Skills with twelve simple, intermediate, and advanced examples and a downloadable practice kit.
How to Automate a Weekly SEO Review with Codex and Search Console
Install a repository Codex skill, connect read-only Search Console data, and run a weekly one-page SEO review with a clear no-change outcome.
GPT-6 Sol and Luna vs Claude Opus 5.5: Which Costs Less to Finish Real Tasks?
From two independent task benchmarks, Luna had the lowest calculated model spend per pass. Opus beat Sol on coding cost per pass; Sol beat Opus on workflows at similar completion rates.
GPT-6 vs GPT-5.6 in Codex: Six Models, Credits, and Token Costs
Compare all six GPT-6 and GPT-5.6 models, see what Codex credits and API tokens cost, and choose a model for coding, agent tasks, and repeated work.
Can One Agent Skill Work in Both Codex and Grok Build?
One SKILL.md can work in Codex and Grok Build. Download the exact Markdown-link checker used in both hosts, compare the complete files, and see which discovery and permission behaviors still need separate tests.
Can an AI Agent Edit an Excel Workbook Without Breaking Formulas? A Univer CLI Test
A Univer CLI test preserved eight formula strings and correct caches through five typed edits, but the export lost the source workbook's checkbox cell-control metadata.
Grok 4.7 vs GPT-6 Astra: Which Coding Agent Finishes the Job?
Codex with GPT-6 Astra and Grok Build with Grok 4.7 fixed the same cross-file Python task. See exact times, tests, diffs, route warnings, and limits.
20 ChatGPT Photo Editing Prompts, With Actual Before-and-After Results
See 20 practical ChatGPT photo editing prompts beside the original image and actual edited output. Each example explains when to use it, what changed, and what to inspect before publishing.
How to Build and Verify a Python AI Endpoint on Cloudflare's Free Plan
Create a Python Workers AI endpoint on Cloudflare Free, test its route and inference, estimate neuron use, and diagnose quota and runtime failures.
How to Hand Off a Coding Task from Claude Code to Codex with ai-memory
Connect both CLIs to ai-memory, end the Claude Code session, and open Codex in the same checkout. Check the handoff against Git, diagnose missing context, and choose between hooks and managed workstreams.
How to Search Local Markdown Notes with QMD and Verify the Results
Set up a QMD collection, compare keyword and semantic hits, inspect the full source note, and reproduce stale-index and deleted-file checks with a downloadable fixture.
How to Use ChatGPT Voice to Manage Codex Tasks on Desktop
Use ChatGPT Voice to start and follow Codex desktop tasks. Learn how to target the right project, verify a test run, switch tasks, and avoid permission and screen-context surprises.
Qwen-Image-2.1 for Production Assets: What a 196-Image Test Supports
A production-focused reading of Li's 196-output Qwen-Image-2.1 report: what the examples support, where they fail, and which acceptance checks matter before shipping an asset.
How to Test Product Video Continuity: Gemini Omni 1.1 Flash vs Grok Imagine Video 1.5 vs Seedance 2.5
Compare three video models with one Pinefold image, documented reference-image requests, and a timestamped continuity scorecard. Protocol only; no model results.
Suno v6 Free vs Paid: What Can You Create, Download, and Reuse?
Compare Suno v6 Free, Pro, and Premier for generation credits, v6 model access, monthly downloads, WAV and stem export, commercial use, and remix rights.
CLAUDE.md vs AGENTS.md in Claude Code: Which Instructions Actually Load?
Claude Code can read AGENTS.md directly, but a project CLAUDE.md or CLAUDE.local.md changes the default. Check the loader setting, version, and session output before changing your repository.
How to Animate an Old Family Photo With AI Responsibly
Choose the right kind of motion for an old family photo, check MyHeritage privacy settings, inspect face and scene changes, and share the result as a simulation.
Qwen3.8-Omni-Flash Video Analysis Test: Can It Find the Right Moment and Support Its Answer?
In one original short-video test, Qwen3.8-Omni-Flash found the saved review window and final status, refused an invented metric, and made one unsupported future-state inference.
What Is Jev AI? How to Use TypeSafe's Decision Model
Jev answers predefined questions about text with typed choices, scores, or yes probabilities. Learn when that helps, how to make a first call, and how to check a routing workflow against your own cases.
How to Audit Agent Permissions Using OpenAI's Model Misalignment Reports
Audit an AI agent's effective authority by turning OpenAI's misalignment reports into staging tests with observable pass conditions and external evidence.
DaVinci Resolve 21.1 MCP With Codex: Setup, Capabilities, and Limitations
Connect Codex to DaVinci Resolve Studio 21.1, check the right project, rename clips, prepare vertical edits, and inspect exports. Includes Free-edition limits and fixes for common failures.
How to Automate Talking-Head Editing With Codex and Jianying
Use Codex to plan a talking-head rough cut, protect names and complete ideas, compile frame-aligned edits, and hand an editable Jianying draft to a human reviewer.
How to Turn a Source-Linked Report Into an Accessible Interactive Web Page With AI
Turn a source-linked report into an accessible interactive web page without losing citations, denominators, limitations, or approval state. Follow a tested conversion with downloadable HTML and checks.
How to Translate Text in an Image With AI Without Breaking the Layout
Translate image text without damaging the design: choose the right workflow, catch OCR omissions, fit each text box, and verify the final export.
Claude Opus 4.6 vs Gemini 3.8 Flash: Which Wins for Coding Agents?
Choose between Claude Opus 4.6 and Gemini 3.8 Flash with current prices, IDE billing considerations, six coding scenarios, repository checks, and private-code data policies.
Grok 4.6 vs Gemini 3.8 Flash for Building an Interactive Web App
Compare Grok 4.6 and Gemini 3.8 Flash for one interactive web app using current WebDev results, API limits, response speed, cost, and a matched acceptance test.
Hypit Review: Can an AI Agent Clone, Edit, and Reuse an Editable Video Workflow?
Hypit turns a reference video or brief into an agent-authored project with semantic timing, reusable components, Build Results, and a Studio timeline. This independent review separates the documented system from the one-click cloning claim.
How to Install and Test DeepSeek Harness Safely
Install DeepSeek Harness in a disposable VM, pin the reviewed dsh version, disable telemetry, start read-only, and verify both a denied mutation and one controlled workspace write.
Hostinger AI Builder: Build and QA a Small-Business Site Before You Publish
Build a small-business site with Hostinger AI Builder, verify its copy, mobile layout, links, contact form, SEO, and domain, then publish with a bounded smoke test.