SuperDoc tools work with any LLM provider or agent framework that supports tool use. The SDK provides tool definitions, schema formatting, and a dispatch function — you write the conversation loop.
LLM tools are in alpha. Tool names and schemas may change between releases.
AWS Bedrock
npm install @superdoc-dev/sdk @aws-sdk/client-bedrock-runtime
import { BedrockRuntimeClient, ConverseCommand } from '@aws-sdk/client-bedrock-runtime';
import { createSuperDocClient, chooseTools, dispatchSuperDocTool } from '@superdoc-dev/sdk';
const client = createSuperDocClient();
await client.connect();
await client.doc.open({ doc: './contract.docx' });
// Get tools in Anthropic format, convert to Bedrock toolSpec shape
const { tools } = await chooseTools({ provider: 'anthropic' });
const toolConfig = {
tools: tools.map((t) => ({
toolSpec: {
name: t.name,
description: t.description,
inputSchema: { json: t.input_schema },
},
})),
};
const bedrock = new BedrockRuntimeClient({ region: 'us-east-1' });
const messages = [
{ role: 'user', content: [{ text: 'Review this contract.' }] },
];
while (true) {
const res = await bedrock.send(new ConverseCommand({
modelId: 'us.anthropic.claude-sonnet-4-6',
messages,
system: [{ text: 'You edit .docx files using SuperDoc tools. Use tracked changes for all edits.' }],
toolConfig,
}));
const output = res.output?.message;
if (!output) break;
messages.push(output);
const toolUses = output.content?.filter((b) => b.toolUse) ?? [];
if (!toolUses.length) break;
const results = [];
for (const block of toolUses) {
const { name, input, toolUseId } = block.toolUse;
const result = await dispatchSuperDocTool(client, name, input ?? {});
const json = typeof result === 'object' && result !== null ? result : { result };
results.push({ toolResult: { toolUseId, content: [{ json }] } });
}
messages.push({ role: 'user', content: results });
}
await client.doc.save();
await client.dispose();
pip install superdoc-sdk boto3
import boto3
from superdoc import SuperDocClient, choose_tools, dispatch_superdoc_tool
client = SuperDocClient()
client.connect()
client.doc.open({"doc": "./contract.docx"})
# Get tools in Anthropic format, convert to Bedrock toolSpec shape
sd_tools = choose_tools({"provider": "anthropic"})
tool_config = {
"tools": [
{
"toolSpec": {
"name": t["name"],
"description": t["description"],
"inputSchema": {"json": t.get("input_schema", {})},
}
}
for t in sd_tools["tools"]
]
}
bedrock = boto3.client("bedrock-runtime", region_name="us-east-1")
messages = [{"role": "user", "content": [{"text": "Review this contract."}]}]
while True:
response = bedrock.converse(
modelId="us.anthropic.claude-sonnet-4-6",
messages=messages,
system=[{"text": "You edit .docx files using SuperDoc tools. Use tracked changes for all edits."}],
toolConfig=tool_config,
)
output = response["output"]["message"]
messages.append(output)
tool_uses = [b for b in output.get("content", []) if "toolUse" in b]
if not tool_uses:
break
tool_results = []
for block in tool_uses:
tu = block["toolUse"]
result = dispatch_superdoc_tool(client, tu["name"], tu.get("input", {}))
json_result = result if isinstance(result, dict) else {"result": result}
tool_results.append(
{"toolResult": {"toolUseId": tu["toolUseId"], "content": [{"json": json_result}]}}
)
messages.append({"role": "user", "content": tool_results})
client.doc.save()
client.dispose()
aws configure, env vars, or IAM role. No API key needed.
Best practices
- Feed errors back. When a tool call fails, return the error as a tool result. Most models self-correct on the next turn.
- Pin your model version. Use a specific model ID (e.g.
us.anthropic.claude-sonnet-4-6) rather than an alias to avoid behavior changes between releases.
- Use tracked changes for review workflows. Add “Use tracked changes for all edits” to the system prompt so a human can accept or reject each change.
Example repository
Complete, runnable examples are available at examples/ai/.
- LLM Tools — tool selection, dispatch, and the full API
- Skills — reusable prompt templates
- MCP Server — Model Context Protocol integration
- SDKs — typed Node.js and Python wrappers
