[dead]
Code mode yields a 99.2% cost reduction in our systems
11–20 of 77 posts
Re: Code mode yields a 99.2% cost reduction in our systems
#12I am once again asking for people to ask Claude to reformat their article text to ASD-STE100 so that I don't have to read slop
Re: Code mode yields a 99.2% cost reduction in our systems
#13The article is so painful to read.
Yes and it’s also something that was already known and recommended. It’s not “code mode” or something revolutionary, it’s just instructing your LLM to feel free to write scripts to aid it in completing the task.
It’s very useful and I use it all the time, and in the end you can distill it into a reusable toolbox, somewhat similar to a collection of markdown files with project knowledge.
Re: Code mode yields a 99.2% cost reduction in our systems
#14The article is so painful to read.
Because it was probably written by an LLM.
Use a LLM to summarize it.
Re: Code mode yields a 99.2% cost reduction in our systems
#15The problem is that when the LLM writes ad-hoc code how can you trust it?
For example in my Liveclip MCP server I'm working on (not released yet) I have table manipulation type tools
So for example a couple days ago Claude made a combined ranking score for my Youtube Shorts analytics -- it did all these tool calls in the same turn
First it normalized the % values into numbers
{ "destination_col": "G", "key": "cinemasleepstories_temp_2026071702", "pattern": "%", "replacement": "", "source": { "col": "E", "row_start": 1, "row_end": 6 } }
Then it made the composite score
{ "dest_col_start": "H", "dest_row_end": 6, "dest_row_start": 1, "expr": "round((likes+1)(followers+1)stayed, 1)", "source_key": "cinemasleepstories_temp_2026071702", "sources": [ { "col": "C", "name": "likes", "row_offset": 0 }, { "col": "D", "name": "followers", "row_offset": 0 }, { "col": "G", "name": "stayed", "row_offset": 0 } ] }
And then it set the new headers
{ "headers": { "G": "Stayed (numeric)", "H": "Composite Score" }, "key": "cinemasleepstories_temp_2026071702" }
If Claude just said "let me write some pandas against this CSV" the workflow would be a lot more iffy and generally uncomfortable/ephemeral
Re: Code mode yields a 99.2% cost reduction in our systems
#16Hi there! We've been building https://github.com/desplega-ai/agent-swarm in the open for a while, and one of the things we wanted to do since the start is find how powerful it can be to push for a code mode like env for the swarm. We tried it and we managed to reduce up +90% of token costs by using swarm scripts (the code mode variant we implemented) for some of our schedules. This is game changer, as we are able to…
We didn't add this for the post. It's just what the swarm already does, and it's the same machinery behind Script Workflows. What we hadn't done is measure it against Anthropic's own yardstick, with our own production data. You say here that "since the start" you wanted to do a "code mode like env". But the LLM that wrote your blog post says your system was already doing this and you just hadn't measured it...? How i…
Hi, the blog post was written assisted with our own swarm, based on the experiment.
Indeed we had the concept of workflows from the start (like n8n), but the point of the scripts is type safe executions that the agents can write, with access to APIs, MCPs, etc.
E.g. this PR from ~10 days ago https://github.com/desplega-ai/agent-swarm/pull/934 was going in this direction, offering a way to defined type safe connections to able to use more the scripts instead of adding MCPs or tools.
e.g. offering a way to do `ctx.api.gmail.searchEmail` coming from an OpenAPI spec.
The whole point of this blog is the "dumb" realisation of the following:
If you have an agent (say Claude Tag, or some other fancy Slack bot) that you keep asking the same things (e.g. check DataDog error and correlate PRs on a timeframe) and the agent does that process agentically, you are wasting tokens.
Now, if you give a way for the agents to write these scripts (code mode) the next time a task like that happens then essentially you just run that and you get easily 90% cost reduction in THAT process. Not globally, obviously.
Re: Code mode yields a 99.2% cost reduction in our systems
#17Hi there! We've been building https://github.com/desplega-ai/agent-swarm in the open for a while, and one of the things we wanted to do since the start is find how powerful it can be to push for a code mode like env for the swarm. We tried it and we managed to reduce up +90% of token costs by using swarm scripts (the code mode variant we implemented) for some of our schedules. This is game changer, as we are able to…
There might be something valuable in this article, but if the you couldn't be bothered to write it yourself, why should we be bothered to read it?
Re: Code mode yields a 99.2% cost reduction in our systems
#18LLM-assisted websites yield a 99.2% trust reduction in me
Re: Code mode yields a 99.2% cost reduction in our systems
#19Re: Code mode yields a 99.2% cost reduction in our systems
#20The problem is that when the LLM writes ad-hoc code how can you trust it? For example in my Liveclip MCP server I'm working on (not released yet) I have table manipulation type tools So for example a couple days ago Claude made a combined ranking score for my Youtube Shorts analytics -- it did all these tool calls in the same turn First it normalized the % values into numbers { "destination_col": "G", "key": "cinemas…
A python script is now more iffy than a LLM going through JSON?