> ## Documentation Index
> Fetch the complete documentation index at: https://hub.hcompany.ai/llms.txt
> Use this file to discover all available pages before exploring further.
> ## Agent Instructions
> H Platform has four products: the Agents API (managed computer-use agents, base URL https://agp.eu.hcompany.ai/api/v2 or https://agp.hcompany.ai/api/v2 for the US), the Models API (OpenAI-compatible Holo vision-language models at https://api.hcompany.ai/v1), HoloDesktop CLI (Holo on the user's own desktop), and HoloTab (a free no-code Chrome extension that runs Holo in the user's browser, with recordable routines and schedules).
> Authenticate with a bearer API key from the HAI_API_KEY environment variable. SDKs: `pip install hai-agents` (Python, `from hai_agents import Client`) and `npm install hai-agents` (TypeScript, `import { HaiAgentsClient } from "hai-agents"`). CLI: `hai`.
> Agents do work in a browser or on a desktop; describe the task as an imperative instruction. To run a task quickly, prefer the pre-built agent `h/web-surfer-flash`. Read results from the session's `latest_answer` after it reaches a terminal status.
> Sessions are the unit of work; wait for a terminal status (completed, failed, timed_out, interrupted) before reading the answer. Use webhooks or the `changes` long-poll endpoint to follow progress.
# Function calling
> The Holo3.1 agent loop with OpenAI-style tools and tool_calls, and the mistakes specific to this format.
export const ChatStrip = ({rows, repeatFrom = 1}) => {
const Body = ({text}) => text.split(/(`[^`]+`)/).map((part, i) => part.startsWith("`") ? {part.slice(1, -1)} : {part});
const Row = ({role, body}) =>
;
};
Holo3.1 (`holo3-1-35b-a3b`) speaks the standard OpenAI tool-calling API, its most natural format, so it plugs into agent frameworks that already do.
Holo3 (`holo3-122b-a10b`) does not support `tools`. Use [structured outputs](/models-api/build-an-agent/structured-outputs) for it.
Read [Core concepts](/models-api/build-an-agent/core-concepts) first: reasoning, coordinates, observations, and the `trim_to_last_n_images` helper used below.
## Declare tools
Pass tool schemas via `tools`, and set `tool_choice="required"` so the model acts on every step. Do not put tool-format examples in the system prompt. The model renders the call in its own native format from `tools` alone, and a conflicting example degrades quality. The example ships two tools (click, answer) for illustration. Real agents register a wider toolbox following the same pattern.
```python Python expandable theme={"system"}
tools = [
{
"type": "function",
"function": {
"name": "click",
"description": "Click at (x, y) coordinates",
"parameters": {
"type": "object",
"properties": {
"element": {"type": "string", "description": "Detailed description of the target UI element"},
"x": {"type": "integer", "description": "X coordinate as integer in [0, 1000]"},
"y": {"type": "integer", "description": "Y coordinate as integer in [0, 1000]"},
},
"required": ["element", "x", "y"],
},
},
},
{
"type": "function",
"function": {
"name": "answer",
"description": "Provide a final answer",
"parameters": {
"type": "object",
"properties": {"content": {"type": "string", "description": "The answer content"}},
"required": ["content"],
},
},
},
]
```
```typescript TypeScript expandable theme={"system"}
const tools = [
{
type: "function",
function: {
name: "click",
description: "Click at (x, y) coordinates",
parameters: {
type: "object",
properties: {
element: { type: "string", description: "Detailed description of the target UI element" },
x: { type: "integer", description: "X coordinate as integer in [0, 1000]" },
y: { type: "integer", description: "Y coordinate as integer in [0, 1000]" },
},
required: ["element", "x", "y"],
},
},
},
{
type: "function",
function: {
name: "answer",
description: "Provide a final answer",
parameters: {
type: "object",
properties: { content: { type: "string", description: "The answer content" } },
required: ["content"],
},
},
},
] as const;
```
## Chat layout
Tool results go back as `tool`-role messages keyed by `tool_call_id`:
` screenshot and/or text ``" },
{ role: "assistant", body: "`tool_calls: [{ id, function: { name, arguments } }]`" },
{ role: "tool", body: "`tool_call_id` matching the call, plus the result" },
]}
/>
## A complete loop
The action comes back in `message.tool_calls`; each call carries a `function.name`, a JSON `function.arguments` string, and a unique `id`. There is no `note` field in this format: anything the model must carry across turns goes in the assistant `content`. Highlighted lines are the ones specific to function calling; everything else is the shared loop from [Core concepts](/models-api/build-an-agent/core-concepts). Plug in your own `screenshot()` (browser, OS, emulator) and `execute(name, args)` dispatcher.
```python Python highlight={18-19,25-26,32-36} theme={"system"}
import json, base64
messages = [{"role": "system", "content": render_prompt()}]
for _ in range(MAX_STEPS):
image_bytes = screenshot()
b64 = base64.b64encode(image_bytes).decode()
messages.append({"role": "user", "content": [
{"type": "text", "text": "\n"},
{"type": "image_url", "image_url": {"url": f"data:image/png;base64,{b64}"}},
{"type": "text", "text": "\n"},
]})
trim_to_last_n_images(messages, n=3)
resp = client.chat.completions.create(
model=MODEL_NAME,
messages=messages,
tools=tools,
tool_choice="required",
temperature=0.8,
)
msg = resp.choices[0].message
messages.append(msg)
call = msg.tool_calls[0]
args = json.loads(call.function.arguments)
if call.function.name == "answer":
return args["content"]
result = execute(call.function.name, args)
messages.append({
"role": "tool",
"tool_call_id": call.id,
"content": str(result),
})
```
```typescript TypeScript highlight={18-19,25-26,33-37} theme={"system"}
const messages: any[] = [{ role: "system", content: renderPrompt() }];
for (let i = 0; i < MAX_STEPS; i++) {
const b64 = (await screenshot()).toString("base64");
messages.push({
role: "user",
content: [
{ type: "text", text: "\n" },
{ type: "image_url", image_url: { url: `data:image/png;base64,${b64}` } },
{ type: "text", text: "\n" },
],
});
trimToLastNImages(messages, 3);
const resp = await client.chat.completions.create({
model: MODEL_NAME,
messages,
tools,
tool_choice: "required",
temperature: 0.8,
});
const msg = resp.choices[0].message;
messages.push(msg);
const call = msg.tool_calls![0];
const args = JSON.parse(call.function.arguments);
if (call.function.name === "answer") {
return args.content;
}
const result = await execute(call.function.name, args);
messages.push({
role: "tool",
tool_call_id: call.id,
content: String(result),
});
}
```
## Format-specific pitfalls
| Symptom | Likely cause |
| :--------------------------------- | :-------------------------------------------------------------------------------------------------- |
| Tool calls come back as plain text | `tool_choice` not set to `required`, or the system prompt contains conflicting tool-format examples |
| Tool result ignored | Sent as a `user` message instead of a `tool`-role message with a matching `tool_call_id` |
| Model forgets earlier facts | Nothing written to the assistant `content` |
## Next steps
Get click coordinates from a screenshot.
Endpoint, models, parameters, and limits.