Prompting Guide
Get the best results from every AEOForged tool. This guide covers per-tool parameter strategies, recommended workflows, and the common mistakes that cost credits or reduce output quality.
General Principles
What is AEO?
Answer Engine Optimization (AEO) is the practice of structuring content so that AI-powered answer engines — ChatGPT, Perplexity, Google AI Overviews, Copilot — can extract, cite, and surface it accurately. Unlike traditional SEO, AEO prioritises direct answerability, entity clarity, and structured data over link-based signals.
Why structure matters
Answer engines don't read pages like humans — they extract fragments. Content with clear headings, concise definitions, lists, and schema markup is far more likely to be pulled into an answer panel. AEOForged tools help you optimise for this extraction pattern.
How scoring works
Every piece of content is scored across 8 dimensions on a 0–100 scale: Structure, Direct Answer, Schema, Entity Coverage, E-E-A-T, Recency, Readability, and Extractability. The overall AEO score is a weighted sum. Pass your research data into the score call to unlock per-section feedback with entity gaps and competitor coverage analysis.
Writing effective briefs (biggest quality lever)
The brief field is available on research, outline, write, and pipeline tools. A good brief can improve first-pass scores by 10-20 points. Include:
- Target audience: Who is reading this? (e.g. "DevOps engineers with 3+ years experience")
- Brand voice: Tone and style constraints (e.g. "conversational but authoritative, never use passive voice")
- Goal: What should the reader do after reading? (e.g. "sign up for the free tier")
- Required angles: Specific topics/entities that must be covered
- Constraints: Word count, sections to avoid, competitors to address
Example: "2500-word article for indie hackers building SaaS businesses. Conversational tone, include real revenue numbers and case studies. Must cover pricing strategy, customer acquisition via content marketing, and the specific AEOForged+Claude workflow for automated content production."
Per-Tool Tips
Organised by workflow phase. Click a tool name to jump to its API reference.
Create Phase
aeo_research10–15 credits- depth:
standard(10cr) for quick factual checks or narrow topics.deep(15cr, uses gpt-4o) for comprehensive multi-angle research on broad topics. - region: Set to a two-letter country code (e.g.
us,gb) to localise search results. Omit for global coverage. - recency: Prefer
weekormonthfor trending topics;yearfor evergreen content. - brief: A focused brief improves entity coverage. Include the target audience and specific angles you want explored.
aeo_outline3 credits- contentType:
articleproduces a long-form narrative outline.faqgenerates question-first structure.productfocuses on features/benefits.guideproduces step-by-step how-to structure. - Writing a good brief: Include your target keyword, audience, desired length, and any angles or entities that must be covered. Example: "2000-word guide on container security for DevOps engineers. Must cover runtime scanning, image signing, and SBOM generation."
aeo_write8 credits- tone:Provide a short description like "professional but approachable" or "technical and concise".
- readingLevel: Controls vocabulary and sentence complexity. Use
generalfor broad audiences,expertfor technical readers. - Citations: Only URLs found in the research results are used as citations. Fabricated sources are filtered out automatically.
aeo_polish2 credits- Idempotent: Safe to run multiple times — the tool detects already-polished content and makes minimal changes on subsequent passes.
- brandVoice: Provide explicit style rules. Examples: "Never use passive voice", "Always use Oxford commas", "Capitalise product names but not features".
- Headings and structure are preserved — polish only affects sentence-level style, not document architecture.
aeo_verify2 credits- Always verify: Run verification after every write/polish pass. Ungrounded claims that slip through writing will be caught here.
- What happens: Claims that can't be verified are either removed (if non-essential) or qualified with hedging language ("some sources suggest…"). Nothing is silently left unverified.
Analyze Phase
aeo_scoreFree- Instant scoring across all 8 AEO dimensions plus an overall weighted score with extractability bonus.
- When to score: After every edit. It's free — use it as a feedback loop to see which changes actually improve your content.
- Each dimension gets a 0–100 score. Focus on your lowest dimensions first for maximum improvement per edit.
aeo_audit5 credits- With targetKeyword: Adds competitive research context — compares your content against top-ranking results for that keyword.
- Without targetKeyword: Standalone audit that evaluates content on its own merits.
- Accepts a URL (fetches the page) or raw markdown. URLs get richer analysis since the tool can inspect meta tags, schema markup, and page structure.
- Reading results: Focus on
improvements(prioritised fixes),missingEntities(gaps in coverage), andschemaOpportunities(structured data you should add).
aeo_compare3 credits- URL vs markdown: URLs get JSON-LD detection and full page analysis; markdown skips schema detection. Prefer URLs when available.
- targetKeyword: When provided, the comparison is contextualised for that keyword — useful for competitive gap analysis.
- marginOfVictory: The point spread between the two pieces. A margin <5 means the pieces are near-equal; >15 indicates clear winner.
aeo_extractFree- Format-specific: Use
featured_snippet,knowledge_panel, orpeople_also_askto target a specific extraction format. Useallto get every format at once. - scoreBreakdown: Shows how well your content fits each extraction format. Use this to decide which format to optimise for.
aeo_crawlabilityFree- Pass any website URL. Returns pass/fail for 11 AI bots, llms.txt presence, sitemap check, JS rendering assessment, and prioritised fix recommendations.
- Best practice: Use as the first step before any audit to catch hard blockers that would prevent AI engines from accessing the content at all.
aeo_llms_txt3 credits- Auto-discovers pages and groups them into semantic sections. Produces both standard
llms.txtand extendedllms-full.txt. - Deliverables: Include the deployment instructions in client deliverables — the output contains exact file contents and hosting guidance.
Maintain Phase
aeo_refresh8 credits- Accepts a URL (fetches latest version) or raw markdown. URLs are preferred for live-content freshness checks.
- content_is_fresh status: If the tool returns this status, your content is already up-to-date — no refresh is needed and no credits are wasted on unnecessary rewrites.
- confidenceLevel: High confidence means the refresh suggestions are well-supported by fresh sources. Low confidence means some suggestions are speculative — review before applying.
aeo_share_of_voice10 credits- Track up to 20 keywords across 3 engines (Brave, Google AI, Perplexity). Compare client domain vs up to 5 competitors.
- Returns:SOV %, coverage, gap keywords (competitors appear but client doesn't), and domination keywords.
- Best practice: Run monthly for trend tracking — SOV shifts over time reveal whether your content strategy is gaining or losing ground.
aeo_cluster5 credits- Optimal keyword count: 20–100 keywords is the sweet spot. Fewer than 20 produces trivial clusters; more than 100 increases noise. Hard cap is 200.
- domain:Providing your domain gives the tool context about your site's existing authority and content, improving cluster relevance.
- hallucinatedKeywords: These keywords were invented by the LLM to fill gaps — they were not in your input. Review them: some are useful suggestions, others should be discarded.
- maxClusters: Leave unset for automatic grouping, or set to constrain the output. Useful when you have a fixed content calendar with N slots.
Pipeline
aeo_full_pipeline12–20 credits- Draft mode (12cr): Runs research → outline → write. Skips polish and verify — ideal for first drafts you plan to iterate on.
- Publish mode (20cr): Full chain: research → outline → write → polish → verify. Production-ready output in one call.
- Pass pre-computed research: If you already ran
aeo_researchseparately, pass the result to save 10cr on the pipeline. The pipeline will skip the research step and use your data directly.
Common Mistakes
Avoid these pitfalls to save credits and get better results.
Sending raw HTML instead of markdown
All tools expect clean markdown input. Raw HTML adds noise, confuses entity extraction, and inflates token counts. Strip HTML or use a URL input instead.
Skipping research before outline
The outline tool produces significantly better structure when it has research context. Without it, outlines lack entity coverage and miss important sub-topics.
Not verifying after writing
The write tool can produce plausible-sounding but ungrounded claims. Always run verify — it catches hallucinated statistics, outdated facts, and unsupported assertions.
Ignoring researchAvailable: false on audit results
When an audit returns researchAvailable: false, its suggestions are based only on structural analysis — not competitive intelligence. Run research separately for keyword-aware recommendations.
Using deep research when standard is sufficient
Deep mode costs 5 extra credits and is only worth it for broad, multi-angle topics. For factual lookups, narrow questions, or single-entity research, standard mode gives equivalent quality at lower cost.
Sending >200 keywords to cluster
The cluster tool caps input at 200 keywords. Beyond ~100, cluster quality degrades as semantic overlap increases. The sweet spot is 20–100 keywords for clean, actionable groupings.
Ready to start?
Try scoring your existing content for free, then work through the Create phase to produce AEO-optimised content.