Esacode

Docs / Blocks / AI

Agent

Reasons over your data in a loop with the LLM you connect, using skills you allow.

Runs on a worker (Python) AI Version 1.0 Code you can open and adapt

How it works

Connect an LLM and the data to work on (files, a table of items, logs). For each item, the agent reads it with its skills (read a file, look at an image, read a log), thinks, and records a decision: a label, a note, keep or reject. Edit the prompts in the settings; open the code to change the harness itself. Limits keep every item within a number of steps and tokens.

Inputs

InputTakesWhat it is
LLM
llm
Model
Data
data
Anything Takes several connections.

Outputs

OutputGivesWhat it is
Decisions
decisions
Table
csv
decisions.csv: one row per item with its label, confidence and reasoning
Report
report
Text
md
Totals
result
Metrics
json
Live telemetry
telemetry
Live telemetryWhat the block sends while it runs, for views such as Chart or 3D view.

Settings

SettingDefaultWhat it does
System prompt
system_prompt
You are a careful reviewer of robotics data. Look at each item, use the tools to inspect …
Task for each item
task_prompt
Item: {name} · Decide whether this item shows a failure worth turning into a simulation s…
Allowed labels
labels
keep, reject
Skills
skills
read_text, view_image, list_files, decide Comma-separated: read_text, view_image, read_table, list_files, note, decide
At most (items)
max_items
50
From 1 to 100000
Steps per item
max_steps
6
From 1 to 50
Token budget for the run
max_tokens_total
200000
From 1000

Where it runs

On one of your computers with the EsaSim worker: Any worker.

In its code, settings are ctx.params["key"], inputs ctx.inputs["id"] and outputs ctx.output("id", "name.ext"); see Custom blocks.

More in AI