brannn

Runcell: AI Coding Assistants in Isolated Workspaces

The Problem

AI coding assistants are powerful, but using them today means dealing with manual configuration, exposing API keys, and hoping the AI doesn't accidentally touch something it shouldn't. Every new project requires the same tedious setup dance—install the tool, configure the provider, manage the keys, repeat.

Runcell changes this by letting Claude handle all of that for you. When you ask Claude to build something, it can spin up an isolated workspace with a pre-configured AI assistant inside, delegate the work, and report back the results. The complexity happens behind the scenes while you focus on describing what you want.

How It Works

brannn

Runcell: AI Coding Assistants in Isolated Workspaces

What Problem Does This Solve?

You want to use AI coding assistants to help write code, but:

• You don't want AI touching your local machine or production systems
• You need different AI providers for different tasks (fast inference vs high quality)
• You want AI to work in clean, reproducible environments
• Setting up AI tools manually is tedious and error-prone

brannn

Inner AI Auto-Configuration Workflow

The Vision: Outer Claude Orchestrates Inner AI

The workflow allows outer Claude (running in Claude Code) to create isolated workspaces with pre-configured AI coding assistants, then delegate tasks to the inner AI running inside those workspaces.

How It Works

┌─────────────────────────────────────────────────────────────────────┐

brannn

import json
import polars as pl
from pyiceberg.catalog import load_catalog
from pyiceberg.schema import Schema
from pyiceberg.types import (
    NestedField,
    LongType,
    StringType,
    TimestampType,
    DoubleType

brannn

Keybase proof

I hereby claim:

• I am heavyliftco on github.
• I am brandonh (https://keybase.io/brandonh) on keybase.
• I have a public key ASAQbkgBQvCY45JK0Kykc6Y_11w2F4zSbXvh19zkL3O4AQo

To claim this, I am signing this object:

brannn

SELECT
  datname, 
  NOW() - query_start AS duration, 
  procpid, 
  current_query 
FROM
  pg_stat_activity 
WHERE
    current_query <> '<IDLE>'
  AND

brannn

#!/usr/bin/env python

import argparse

import boto.ec2.elb
import boto.ec2

parser = argparse.ArgumentParser(description="Get ELB instances by release tag")
parser.add_argument("-region", "--region",    
                   metavar="region",    

brannn

#!/bin/bash

if [ $# -eq 0 ]; then
    echo >&2 "Usage: jstackSeries  [  [  ] ]"
    echo >&2 "    Defaults: count = 10, delay = 1 (seconds)"
    exit 1
fi

pid=$1          # required
count=${2:-10}  # defaults to 10 times

brannn

#python2.7
{k:int(v) if v.isdigit() else v for k,v in DATABASE.iteritems()}
 
 #python3
k:int(v) if v.isdigit() else v for k,v in DATABASE.items()}

brannn

CREATE TRIGGER update_last_request BEFORE UPDATE
ON requests FOR EACH ROW EXECUTE PROCEDURE 
update_modified_ctimestamp();