diff --git a/apps/docs/ai/agents/best-practices.mdx b/apps/docs/ai/agents/best-practices.mdx index 6d8518d749..a4c1ee9191 100644 --- a/apps/docs/ai/agents/best-practices.mdx +++ b/apps/docs/ai/agents/best-practices.mdx @@ -81,7 +81,7 @@ When you need to create multiple headings and paragraphs in one operation, use ` After inserting, apply formatting in a single `superdoc_mutations` batch using `format.apply` steps — one step per block or range. This reduces a workflow that might otherwise take 40+ calls down to 4: read, search, insert, format. -## Use focused tools; `superdoc_mutations` is an escape hatch +## Use focused tools — `superdoc_mutations` is an escape hatch For straightforward edits, use the focused intent tools (`superdoc_edit`, `superdoc_format`, `superdoc_create`, `superdoc_list`, `superdoc_comment`). They validate arguments, give clear errors, and are easier for models to call correctly. diff --git a/apps/docs/ai/agents/eval-results.mdx b/apps/docs/ai/agents/eval-results.mdx index 8ca0bd50ea..f2f1d54a18 100644 --- a/apps/docs/ai/agents/eval-results.mdx +++ b/apps/docs/ai/agents/eval-results.mdx @@ -10,7 +10,7 @@ SuperDoc's Document API exposes [360+ operations](/document-api/available-operat **Recommended models** -- **Best overall accuracy — GPT-5.4 (OpenAI):** 100% tool quality score with the full system prompt. Use this for batch processing, async pipelines, and any scenario where latency is not the primary constraint. +- **Best overall accuracy — GPT-5.4 (OpenAI):** 100% tool quality score with the full system prompt. Use this for batch processing, async pipelines, and any case where speed doesn't matter. - **Best for fast responses — Gemini 2.5 Flash (Google):** 94% tool quality score at lower latency. Use this for real-time, interactive editing where speed matters. Claude Haiku 4.5 (Anthropic) is a strong alternative for fast use cases — 90% accuracy with the smallest prompt dependency gap (-13 points), meaning it degrades least when the system prompt is trimmed. diff --git a/apps/docs/ai/agents/llm-tools.mdx b/apps/docs/ai/agents/llm-tools.mdx index 4ad1284056..acc0a81375 100644 --- a/apps/docs/ai/agents/llm-tools.mdx +++ b/apps/docs/ai/agents/llm-tools.mdx @@ -156,7 +156,7 @@ The generated catalog currently contains 9 grouped intent tools. Most tools use | `superdoc_mutations` | `preview`, `apply` | Execute multi-step atomic edits as a batch | -More tools are being added as we expand coverage — tables, images, hyperlinks, and more. You can also [create custom tools](#creating-custom-tools) for any `doc.*` operation today. +Built-in tools cover the core operations. For tables, images, hyperlinks, and anything else, [create custom tools](#creating-custom-tools) that call any `doc.*` operation today. ## Dispatching tool calls @@ -187,7 +187,7 @@ More tools are being added as we expand coverage — tables, images, hyperlinks, -The dispatcher validates required parameters, enforces mutual exclusivity constraints, and throws descriptive errors if arguments are invalid, so the LLM gets actionable feedback. +The dispatcher validates required parameters, checks that arguments are compatible, and throws descriptive errors the LLM can act on. ## System prompt diff --git a/apps/docs/ai/agents/skills.mdx b/apps/docs/ai/agents/skills.mdx index e4df21cb1b..f9b676e605 100644 --- a/apps/docs/ai/agents/skills.mdx +++ b/apps/docs/ai/agents/skills.mdx @@ -1,7 +1,6 @@ --- title: Skills sidebarTitle: Skills -tag: COMING SOON description: Reusable prompt templates that teach LLMs how to edit documents with SuperDoc tools keywords: "llm skills, prompt templates, ai document editing, superdoc skills" --- @@ -9,7 +8,7 @@ keywords: "llm skills, prompt templates, ai document editing, superdoc skills" Skills are reusable prompt files that teach LLMs how to use SuperDoc tools effectively. A skill contains editing instructions, tool usage patterns, and best practices — so your LLM agent knows how to query, mutate, and format documents without trial and error. -Skills are coming soon. Check back for updates. +We haven't shipped skills yet. Follow the repo for updates. ## Related