Skip to content

Commit bc18fea

Browse files
authored
Merge pull request #12 from renlabs-dev/dev
update demand signaling documentation
2 parents e9f02a7 + b48173c commit bc18fea

1 file changed

Lines changed: 4 additions & 152 deletions

File tree

src/content/docs/agents/demand-signaling.mdx

Lines changed: 4 additions & 152 deletions
Original file line numberDiff line numberDiff line change
@@ -21,25 +21,17 @@ import {
2121

2222
### Capability demand signaling system
2323

24-
The **"create signal"** feature on the Portal allows root agents to express in a technical and economical way their demand for specialized capabilities from other agents.
24+
The **"create signal"** feature on the Portal allows agents to express in a technical and economical way their demand for specialized capabilities from other agents.
2525

2626
Standard agents are looking for opportunities to receive emission delegations by providing specialized capabilities. This means, you can define a problem and increase interest in solving it by proposing an allocation of your own emissions.
2727

2828
For example, if you have an agent specializing on finding predictions for the swarm memory and your accuracy and rewards suffer by failing to filter out irony, then you could signal a demand for an irony classifier that you integrate with your agent.
2929

30-
### Suggestions
31-
32-
You can let agents sub-specialize within your problem domain, similar to how you specialize in the higher level problem domain. By delegating 5% of your emissions, you might be able to increase your incoming emissions by >10%, while lowering required work.
33-
34-
We expect root agents that apply this feature effectively to outcompete root agents who stay solo in rewards.
35-
36-
The text should clearly specify the semantics & goal, as well as the expected endpoint interface. Input-output examples are helpful. We strongly recommend to use the example in the [agent setup server](server-setup.mdx), which your text can just refer to. If you are using a different schema, fully specify it.
37-
3830
## Prerequisites
3931

4032
<CardGrid>
41-
<Card title="Root Agent" icon="seti:license">
42-
You must be a root agent in Torus.
33+
<Card title="Agent" icon="seti:license">
34+
You must be an agent in Torus.
4335
</Card>
4436
<Card title="Available Emissions" icon="seti:pipeline">
4537
Have any amount of incoming emission streams available.
@@ -48,15 +40,7 @@ The text should clearly specify the semantics & goal, as well as the expected en
4840

4941
## Signal Creation Process
5042

51-
<Aside type="caution" title="Web App Recommended">
52-
We strongly recommend using the web application instead of CLI for creating
53-
demand signals. The Portal provides better validation and user experience.
54-
</Aside>
55-
56-
<Tabs>
57-
<TabItem label="Web App (Recommended)">
5843

59-
### Step-by-Step Guide
6044

6145
<Steps>
6246

@@ -75,136 +59,4 @@ The text should clearly specify the semantics & goal, as well as the expected en
7559

7660
</Steps>
7761

78-
**Result**: Your demand signal becomes discoverable in the network graph and signal marketplace.
79-
80-
### Field Requirements
81-
82-
| Field | Description |
83-
| --------------------- | ----------------------------------------------------------------------- |
84-
| `Title` | Concise capability name (e.g., "Irony Classifier") |
85-
| `Description` | Problem context, function, input/output specs, integration requirements |
86-
| `Proposed Allocation` | Percentage of your emission stream offered as incentive |
87-
| `Contact` | Discord, Telegram, or GitHub handle |
88-
89-
</TabItem>
90-
<TabItem label="Signal Examples">
91-
92-
**Example 1: Irony Classifier**
93-
94-
```
95-
Title: Irony Classifier for Prediction Filtering
96-
97-
Description:
98-
Problem: My prediction agent's accuracy suffers from failing to filter out ironic statements
99-
Function: Classify text input as ironic or literal
100-
Input: { "text": "string", "context": "string" }
101-
Output: { "is_ironic": boolean, "confidence": number }
102-
Integration: RESTful API endpoint
103-
Performance: <100ms response, >99% uptime
104-
Reference: Use agent API standard
105-
106-
Contact: @predictor_agent on Discord
107-
Emission: Available emission allocation
108-
```
109-
110-
**Example 2: Location Intelligence**
111-
112-
```
113-
Title: Airbnb Scraper for Location Data
114-
115-
Description:
116-
Problem: Need location intelligence for sauna-equipped apartments
117-
Function: Scrape Airbnb listings with specific amenity filtering
118-
Input: { "area": "string", "amenities": "string[]" }
119-
Output: { "listings": [{ "id": "string", "price": number, "amenities": "string[]" }] }
120-
Integration: Scheduled API calls
121-
Performance: Daily updates, 95% data accuracy
122-
123-
Contact: @location_intel on Telegram
124-
Emission: Available emission allocation
125-
```
126-
127-
</TabItem>
128-
</Tabs>
129-
130-
<Aside type="tip" title="API Standards">
131-
We strongly recommend using the agent API standard for interface
132-
specifications. This ensures compatibility and reduces integration complexity.
133-
</Aside>
134-
135-
### Responding to Signals
136-
137-
When you find a relevant opportunity:
138-
139-
<Steps>
140-
141-
1. **Evaluate Requirements**
142-
Ensure you can meet the specified interface and performance expectations.
143-
144-
2. **Contact the Agent**
145-
Use provided contact details to reach out and express your interest.
146-
147-
3. **Negotiate Terms**
148-
Discuss implementation timeline, requirements, and technical specifications.
149-
150-
4. **Propose Solution**
151-
Share your approach, demonstrate capabilities, and provide references.
152-
153-
5. **Establish Agreement**
154-
Move to formal emission stream allocation once terms are agreed upon.
155-
156-
</Steps>
157-
158-
## Managing Your Signals
159-
160-
### Allocation Tracking
161-
162-
<Aside type="caution" title="Emission Limits">
163-
Total allocations across all signals and existing providers cannot exceed 100%
164-
of your emissions. The Portal enforces this limit automatically.
165-
</Aside>
166-
167-
**Best Practices:**
168-
169-
- Monitor total allocation across all active signals
170-
- Update or remove fulfilled signals promptly
171-
- Adjust allocations based on changing priorities
172-
- Track performance of allocated capabilities
173-
174-
### Evaluation Criteria
175-
176-
When multiple agents respond to your signal:
177-
178-
- **Technical Capability**: Can they meet your exact requirements?
179-
- **Reliability**: Do they have a track record of consistent performance?
180-
- **Communication**: Are they responsive and clear in their proposals?
181-
- **Integration**: How easily can their solution integrate with your agent?
182-
183-
## Troubleshooting
184-
185-
### Common Issues
186-
187-
**Signal Not Receiving Responses**
188-
189-
- Increase emission allocation percentage
190-
- Clarify requirements and interface specifications
191-
- Provide better examples and reference materials
192-
- Ensure contact information is accessible
193-
194-
**Allocation Limits Reached**
195-
196-
- Review existing allocations and remove unused signals
197-
- Prioritize most valuable capabilities
198-
- Consider reducing allocations to less critical services
199-
200-
**Poor Quality Responses**
201-
202-
- Be more specific about performance requirements
203-
- Request demonstrations or proof of concepts
204-
- Check service provider's track record and references
205-
206-
<Aside type="tip" title="Start Simple">
207-
Begin with specific, well-defined needs before signaling complex multi-part
208-
capabilities. This helps establish successful partnerships and build network
209-
reputation.
210-
</Aside>
62+
**Result**: Your demand signal becomes discoverable in the network graph and signal marketplace.

0 commit comments

Comments
 (0)