Parallel - Web Research API

Web research API with OpenAI-compatible chat completions and async tasks

How to use it

  1. Hit Copy the whole skill.
  2. Claude: ⋯ → Download .md, then Customize → Skills → Add → Upload skill.
    ChatGPT: make a Project and paste it into Instructions.
    Neither? Paste it at the top of a new chat — it works for that chat.
  3. Describe your job in plain words. The AI follows the skill from there.
Claude Code — installs the whole folder, not just SKILL.md
npx degit gooseworks-ai/goose-skills/skills/research-tools/capabilities/web-research-parallel#main ~/.claude/skills/web-research-parallel

For one project only, change the path to .claude/skills/web-research-parallel.

Not working?
  • Check which app you pasted it into — the steps above name the right one.
  • Some skills need the paid tier of Claude or ChatGPT.
Step-by-step guide with screenshots · Ask in the forum

Paste into Claude, ChatGPT or Cursor.

Show the full text244 lines
web-research-parallel/SKILL.md244 lines11.8 KBpushed 96d agoRawView on GitHub

Parallel - Web Research API

Setup

Read your credentials from ~/.gooseworks/credentials.json:

export GOOSEWORKS_API_KEY=$(python3 -c "import json;print(json.load(open('$HOME/.gooseworks/credentials.json'))['api_key'])")
export GOOSEWORKS_API_BASE=$(python3 -c "import json;print(json.load(open('$HOME/.gooseworks/credentials.json')).get('api_base','https://api.gooseworks.ai'))")

If ~/.gooseworks/credentials.json does not exist, tell the user to run: npx gooseworks login

All endpoints use Bearer auth: -H "Authorization: Bearer $GOOSEWORKS_API_KEY"

Web research API that returns OpenAI ChatCompletions-compatible responses.

Capabilities

  • Retrieve FindAll Run Status: Retrieve a FindAll run (free)
  • FindAll Run Result: Retrieve the FindAll run result at the time of the request (free)
  • Cancel FindAll Run: Cancel a FindAll run (free)
  • Retrieve Task Run Input: Retrieves the input of a run by run_id (free)
  • Retrieve Task Run: Retrieves run status by run_id (free)
  • Ingest FindAll Run: Transforms a natural language search objective into a structured FindAll spec
  • Retrieve Task Run Result: Retrieves a run result by run_id, blocking until the run is completed (free)
  • Create FindAll Run: Starts a FindAll run
  • Search: Searches the web
  • Chat API: Parallel Chat is a web research API that returns OpenAI ChatCompletions compatible streaming text and JSON
  • Extract: Extracts relevant content from specific web URLs
  • Create Task Run: Initiates a task run

Usage

Retrieve FindAll Run Status (free)

Retrieve a FindAll run.

curl -s -X POST $GOOSEWORKS_API_BASE/v1/proxy/orthogonal/run \
  -H "Authorization: Bearer $GOOSEWORKS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"api":"parallel","path":"/v1beta/findall/runs/{findall_id}"}'

FindAll Run Result (free)

Retrieve the FindAll run result at the time of the request.

curl -s -X POST $GOOSEWORKS_API_BASE/v1/proxy/orthogonal/run \
  -H "Authorization: Bearer $GOOSEWORKS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"api":"parallel","path":"/v1beta/findall/runs/{findall_id}/result"}'

Cancel FindAll Run (free)

Cancel a FindAll run.

curl -s -X POST $GOOSEWORKS_API_BASE/v1/proxy/orthogonal/run \
  -H "Authorization: Bearer $GOOSEWORKS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"api":"parallel","path":"/v1beta/findall/runs/{findall_id}/cancel"}'

Retrieve Task Run Input (free)

Retrieves the input of a run by run_id.

curl -s -X POST $GOOSEWORKS_API_BASE/v1/proxy/orthogonal/run \
  -H "Authorization: Bearer $GOOSEWORKS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"api":"parallel","path":"/v1/tasks/runs/{run_id}/input"}'

Retrieve Task Run (free)

Retrieves run status by run_id.The run result is available from the /result endpoint.

curl -s -X POST $GOOSEWORKS_API_BASE/v1/proxy/orthogonal/run \
  -H "Authorization: Bearer $GOOSEWORKS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"api":"parallel","path":"/v1/tasks/runs/{run_id}"}'

Ingest FindAll Run

Transforms a natural language search objective into a structured FindAll spec.Note: Access to this endpoint requires the parallel-beta header.The generated specification serves as a suggested starting point and can be furthercustomized by the user.

Parameters:

  • objective* (string) - Input model for FindAll ingest.
curl -s -X POST $GOOSEWORKS_API_BASE/v1/proxy/orthogonal/run \
  -H "Authorization: Bearer $GOOSEWORKS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"api":"parallel","path":"/v1beta/findall/ingest","body":{"objective":"Find all AI startups in San Francisco"}}'

Retrieve Task Run Result (free)

Retrieves a run result by run_id, blocking until the run is completed.

Parameters:

  • timeout (integer)
curl -s -X POST $GOOSEWORKS_API_BASE/v1/proxy/orthogonal/run \
  -H "Authorization: Bearer $GOOSEWORKS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"api":"parallel","path":"/v1/tasks/runs/{run_id}/result"}'

Create FindAll Run

Starts a FindAll run.This endpoint immediately returns a FindAll run object with status set to ‘queued’.You can get the run result snapshot using the GET /v1beta/findall/runs//result endpoint.You can track the progress of the run by:Polling the status using the GET /v1beta/findall/runs/ endpoint,Subscribing to real-time updates via the /v1beta/findall/runs//eventsendpoint,Or specifying a webhook with relevant event types during run creation to receivenotifications.

Parameters:

  • objective* (string) - Input model for FindAll run.
  • entity_type* (string) - Type of the entity for the FindAll run.
  • match_conditions* (MatchCondition · object[]) - List of match conditions for the FindAll run.
  • generator* (enum<string>) - Generator for the FindAll run. One of base, core, pro, preview.
  • match_limit* (integer) - Maximum number of matches to find for this FindAll run. Must be between 5 and 1000 (inclusive).
  • exclude_list (ExcludeCandidate · object[] | null) - List of entity names/IDs to exclude from results.
  • metadata (Metadata · object) - Metadata for the FindAll run.
  • webhook (Webhook · object) - Webhook for the FindAll run.
curl -s -X POST $GOOSEWORKS_API_BASE/v1/proxy/orthogonal/run \
  -H "Authorization: Bearer $GOOSEWORKS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"api":"parallel","path":"/v1beta/findall/runs"}'
  "goal": "Find all AI startups in San Francisco"
}'

Search

Searches the web.To access this endpoint, pass the parallel-beta header with the valuesearch-extract-2025-10-10.

Parameters:

  • mode (enum<string> | null) - Request to Search API.
  • objective (string | null) - Natural-language description of what the web search is trying to find. May include guidance about preferred sources or freshness. At least one of objective or search_queries must be provided.
  • search_queries (string[] | null) - Optional list of traditional keyword search queries to guide the search. May contain search operators. At least one of objective or search_queries must be provided.
  • processor (enum<string> | null) - DEPRECATED: use mode instead.
  • max_results (integer | null) - Upper bound on the number of results to return. May be limited by the processor. Defaults to 10 if not provided.
  • max_chars_per_result (integer | null) - DEPRECATED: Use excerpts.max_chars_per_result instead.
  • excerpts (object) - Optional settings to configure excerpt generation.
  • source_policy (object) - Optional source policy governing domain and date preferences in search results.
  • fetch_policy (object) - Fetch policy: determines when to return cached content from the index (faster) vs fetching live content (fresher). Default is to disable live fetch and return cached content from the index.
curl -s -X POST $GOOSEWORKS_API_BASE/v1/proxy/orthogonal/run \
  -H "Authorization: Bearer $GOOSEWORKS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"api":"parallel","path":"/v1beta/search","body":{"objective":"AI agent frameworks comparison 2024"}}'

Chat API

Parallel Chat is a web research API that returns OpenAI ChatCompletions compatible streaming text and JSON.

Parameters:

  • model (string)
  • messages (array)
  • stream (boolean)
  • response_format (object)
curl -s -X POST $GOOSEWORKS_API_BASE/v1/proxy/orthogonal/run \
  -H "Authorization: Bearer $GOOSEWORKS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"api":"parallel","path":"/chat/completions"}'
  "model": "parallel",
  "messages": [
    {"role": "user", "content": "What are the latest developments in quantum computing?"}
  ]
}'

Extract

Extracts relevant content from specific web URLs.To access this endpoint, pass the parallel-beta header with the valuesearch-extract-2025-10-10.

Parameters:

  • urls* (string[]) - Extract request.
  • objective (string) - If provided, focuses extracted content on the specified search objective.
  • search_queries (string[]) - If provided, focuses extracted content on the specified keyword search queries.
  • fetch_policy (object) - Fetch policy: determines when to return cached content from the index (faster) vs fetching live content (fresher). Default is to use a dynamic policy based on the search objective and url.
  • excerpts (boolean) - Include excerpts from each URL relevant to the search objective and queries. Note that if neither objective nor search_queries is provided, excerpts are redundant with full content. default:true
  • full_content (boolean) - Include full content from each URL. Note that if neither objective nor search_queries is provided, excerpts are redundant with full content. default:false
curl -s -X POST $GOOSEWORKS_API_BASE/v1/proxy/orthogonal/run \
  -H "Authorization: Bearer $GOOSEWORKS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"api":"parallel","path":"/v1beta/extract","body":{"urls":["https://example.com/article"]}}'

Create Task Run

Initiates a task run.Returns immediately with a run object in status ‘queued’.Beta features can be enabled by setting the ‘parallel-beta’ header.

Parameters:

  • processor* (string) - Task run input with additional beta fields.
  • input* (string) - Input to the task, either text or a JSON object.
  • metadata (object) - User-provided metadata stored with the run. Keys and values must be strings with a maximum length of 16 and 512 characters respectively.
  • source_policy (object) - Optional source policy governing preferred and disallowed domains in web search results.
  • task_spec (object) - Task specification. If unspecified, defaults to auto output schema.
  • mcp_servers (object[]) - Optional list of MCP servers to use for the run.To enable this feature in your requests, specify mcp-server-2025-07-17 as one of the values in parallel-beta header (for API calls) or betas param (for the SDKs).
  • enable_events (boolean) - Controls tracking of task run execution progress. When set to true, progress events are recorded and can be accessed via the Task Run events endpoint. When false, no progress events are tracked. Note that progress tracking cannot be enabled after a run has been created. The flag is set to true by default for premium processors (pro and above).To enable this feature in your requests, specify events-sse-2025-07-24 as one of the values in parallel-beta header (for API calls) or betas param (for the SDKs).
  • webhook (object) - Callback URL (webhook endpoint) that will receive an HTTP POST when the run completes.This feature is not available via the Python SDK. To enable this feature in your API requests, specify the parallel-beta header with webhook-2025-08-12 value.
curl -s -X POST $GOOSEWORKS_API_BASE/v1/proxy/orthogonal/run \
  -H "Authorization: Bearer $GOOSEWORKS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"api":"parallel","path":"/v1/tasks/runs"}'
  "processor": "base",
  "input": "Research the competitive landscape of AI coding assistants"
}'

Use Cases

  1. Research Automation: Get comprehensive research on any topic
  2. OpenAI Drop-in: Use with existing OpenAI SDK code
  3. Competitive Analysis: Research competitors and market
  4. Due Diligence: Gather information for investment decisions

Discover More

For full endpoint details and parameters:

curl -s -X POST $GOOSEWORKS_API_BASE/v1/proxy/orthogonal/search \
  -H "Authorization: Bearer $GOOSEWORKS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"prompt":"parallel API endpoints"}' List all endpoints
curl -s -X POST $GOOSEWORKS_API_BASE/v1/proxy/orthogonal/details \
  -H "Authorization: Bearer $GOOSEWORKS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"api":"parallel","path":"/v1beta/findall"}'   # Get endpoint details
1---
2name: web-research-parallel
3description: Web research API with OpenAI-compatible chat completions and async tasks
4source: orthogonal
5---
6 
7 
8# Parallel - Web Research API
9 
10## Setup
11 
12Read your credentials from ~/.gooseworks/credentials.json:
13```bash
14export GOOSEWORKS_API_KEY=$(python3 -c "import json;print(json.load(open('$HOME/.gooseworks/credentials.json'))['api_key'])")
15export GOOSEWORKS_API_BASE=$(python3 -c "import json;print(json.load(open('$HOME/.gooseworks/credentials.json')).get('api_base','https://api.gooseworks.ai'))")
16```
17 
18If ~/.gooseworks/credentials.json does not exist, tell the user to run: `npx gooseworks login`
19 
20All endpoints use Bearer auth: `-H "Authorization: Bearer $GOOSEWORKS_API_KEY"`
21 
22 
23Web research API that returns OpenAI ChatCompletions-compatible responses.
24 
25## Capabilities
26 
27- **Retrieve FindAll Run Status**: Retrieve a FindAll run (free)
28- **FindAll Run Result**: Retrieve the FindAll run result at the time of the request (free)
29- **Cancel FindAll Run**: Cancel a FindAll run (free)
30- **Retrieve Task Run Input**: Retrieves the input of a run by run_id (free)
31- **Retrieve Task Run**: Retrieves run status by run_id (free)
32- **Ingest FindAll Run**: Transforms a natural language search objective into a structured FindAll spec
33- **Retrieve Task Run Result**: Retrieves a run result by run_id, blocking until the run is completed (free)
34- **Create FindAll Run**: Starts a FindAll run
35- **Search**: Searches the web
36- **Chat API**: Parallel Chat is a web research API that returns OpenAI ChatCompletions compatible streaming text and JSON
37- **Extract**: Extracts relevant content from specific web URLs
38- **Create Task Run**: Initiates a task run
39 
40## Usage
41 
42### Retrieve FindAll Run Status (free)
43Retrieve a FindAll run.
44 
45```bash
46curl -s -X POST $GOOSEWORKS_API_BASE/v1/proxy/orthogonal/run \
47 -H "Authorization: Bearer $GOOSEWORKS_API_KEY" \
48 -H "Content-Type: application/json" \
49 -d '{"api":"parallel","path":"/v1beta/findall/runs/{findall_id}"}'
50```
51 
52### FindAll Run Result (free)
53Retrieve the FindAll run result at the time of the request.
54 
55```bash
56curl -s -X POST $GOOSEWORKS_API_BASE/v1/proxy/orthogonal/run \
57 -H "Authorization: Bearer $GOOSEWORKS_API_KEY" \
58 -H "Content-Type: application/json" \
59 -d '{"api":"parallel","path":"/v1beta/findall/runs/{findall_id}/result"}'
60```
61 
62### Cancel FindAll Run (free)
63Cancel a FindAll run.
64 
65```bash
66curl -s -X POST $GOOSEWORKS_API_BASE/v1/proxy/orthogonal/run \
67 -H "Authorization: Bearer $GOOSEWORKS_API_KEY" \
68 -H "Content-Type: application/json" \
69 -d '{"api":"parallel","path":"/v1beta/findall/runs/{findall_id}/cancel"}'
70```
71 
72### Retrieve Task Run Input (free)
73Retrieves the input of a run by run_id.
74 
75```bash
76curl -s -X POST $GOOSEWORKS_API_BASE/v1/proxy/orthogonal/run \
77 -H "Authorization: Bearer $GOOSEWORKS_API_KEY" \
78 -H "Content-Type: application/json" \
79 -d '{"api":"parallel","path":"/v1/tasks/runs/{run_id}/input"}'
80```
81 
82### Retrieve Task Run (free)
83Retrieves run status by run_id.The run result is available from the /result endpoint.
84 
85```bash
86curl -s -X POST $GOOSEWORKS_API_BASE/v1/proxy/orthogonal/run \
87 -H "Authorization: Bearer $GOOSEWORKS_API_KEY" \
88 -H "Content-Type: application/json" \
89 -d '{"api":"parallel","path":"/v1/tasks/runs/{run_id}"}'
90```
91 
92### Ingest FindAll Run
93Transforms a natural language search objective into a structured FindAll spec.Note: Access to this endpoint requires the parallel-beta header.The generated specification serves as a suggested starting point and can be furthercustomized by the user.
94 
95Parameters:
96- objective* (string) - Input model for FindAll ingest.
97 
98```bash
99curl -s -X POST $GOOSEWORKS_API_BASE/v1/proxy/orthogonal/run \
100 -H "Authorization: Bearer $GOOSEWORKS_API_KEY" \
101 -H "Content-Type: application/json" \
102 -d '{"api":"parallel","path":"/v1beta/findall/ingest","body":{"objective":"Find all AI startups in San Francisco"}}'
103```
104 
105### Retrieve Task Run Result (free)
106Retrieves a run result by run_id, blocking until the run is completed.
107 
108Parameters:
109- timeout (integer)
110 
111```bash
112curl -s -X POST $GOOSEWORKS_API_BASE/v1/proxy/orthogonal/run \
113 -H "Authorization: Bearer $GOOSEWORKS_API_KEY" \
114 -H "Content-Type: application/json" \
115 -d '{"api":"parallel","path":"/v1/tasks/runs/{run_id}/result"}'
116```
117 
118### Create FindAll Run
119Starts a FindAll run.This endpoint immediately returns a FindAll run object with status set to ‘queued’.You can get the run result snapshot using the GET /v1beta/findall/runs//result endpoint.You can track the progress of the run by:Polling the status using the GET /v1beta/findall/runs/ endpoint,Subscribing to real-time updates via the /v1beta/findall/runs//eventsendpoint,Or specifying a webhook with relevant event types during run creation to receivenotifications.
120 
121Parameters:
122- objective* (string) - Input model for FindAll run.
123- entity_type* (string) - Type of the entity for the FindAll run.
124- match_conditions* (MatchCondition · object[]) - List of match conditions for the FindAll run.
125- generator* (enum<string>) - Generator for the FindAll run. One of base, core, pro, preview.
126- match_limit* (integer) - Maximum number of matches to find for this FindAll run. Must be between 5 and 1000 (inclusive).
127- exclude_list (ExcludeCandidate · object[] | null) - List of entity names/IDs to exclude from results.
128- metadata (Metadata · object) - Metadata for the FindAll run.
129- webhook (Webhook · object) - Webhook for the FindAll run.
130 
131```bash
132curl -s -X POST $GOOSEWORKS_API_BASE/v1/proxy/orthogonal/run \
133 -H "Authorization: Bearer $GOOSEWORKS_API_KEY" \
134 -H "Content-Type: application/json" \
135 -d '{"api":"parallel","path":"/v1beta/findall/runs"}'
136 "goal": "Find all AI startups in San Francisco"
137}'
138```
139 
140### Search
141Searches the web.To access this endpoint, pass the parallel-beta header with the valuesearch-extract-2025-10-10.
142 
143Parameters:
144- mode (enum<string> | null) - Request to Search API.
145- objective (string | null) - Natural-language description of what the web search is trying to find. May include guidance about preferred sources or freshness. At least one of objective or search_queries must be provided.
146- search_queries (string[] | null) - Optional list of traditional keyword search queries to guide the search. May contain search operators. At least one of objective or search_queries must be provided.
147- processor (enum<string> | null) - DEPRECATED: use mode instead.
148- max_results (integer | null) - Upper bound on the number of results to return. May be limited by the processor. Defaults to 10 if not provided.
149- max_chars_per_result (integer | null) - DEPRECATED: Use excerpts.max_chars_per_result instead.
150- excerpts (object) - Optional settings to configure excerpt generation.
151- source_policy (object) - Optional source policy governing domain and date preferences in search results.
152- fetch_policy (object) - Fetch policy: determines when to return cached content from the index (faster) vs fetching live content (fresher). Default is to disable live fetch and return cached content from the index.
153 
154```bash
155curl -s -X POST $GOOSEWORKS_API_BASE/v1/proxy/orthogonal/run \
156 -H "Authorization: Bearer $GOOSEWORKS_API_KEY" \
157 -H "Content-Type: application/json" \
158 -d '{"api":"parallel","path":"/v1beta/search","body":{"objective":"AI agent frameworks comparison 2024"}}'
159```
160 
161### Chat API
162Parallel Chat is a web research API that returns OpenAI ChatCompletions compatible streaming text and JSON.
163 
164Parameters:
165- model (string)
166- messages (array)
167- stream (boolean)
168- response_format (object)
169 
170```bash
171curl -s -X POST $GOOSEWORKS_API_BASE/v1/proxy/orthogonal/run \
172 -H "Authorization: Bearer $GOOSEWORKS_API_KEY" \
173 -H "Content-Type: application/json" \
174 -d '{"api":"parallel","path":"/chat/completions"}'
175 "model": "parallel",
176 "messages": [
177 {"role": "user", "content": "What are the latest developments in quantum computing?"}
178 ]
179}'
180```
181 
182### Extract
183Extracts relevant content from specific web URLs.To access this endpoint, pass the parallel-beta header with the valuesearch-extract-2025-10-10.
184 
185Parameters:
186- urls* (string[]) - Extract request.
187- objective (string) - If provided, focuses extracted content on the specified search objective.
188- search_queries (string[]) - If provided, focuses extracted content on the specified keyword search queries.
189- fetch_policy (object) - Fetch policy: determines when to return cached content from the index (faster) vs fetching live content (fresher). Default is to use a dynamic policy based on the search objective and url.
190- excerpts (boolean) - Include excerpts from each URL relevant to the search objective and queries. Note that if neither objective nor search_queries is provided, excerpts are redundant with full content. default:true
191- full_content (boolean) - Include full content from each URL. Note that if neither objective nor search_queries is provided, excerpts are redundant with full content. default:false
192 
193```bash
194curl -s -X POST $GOOSEWORKS_API_BASE/v1/proxy/orthogonal/run \
195 -H "Authorization: Bearer $GOOSEWORKS_API_KEY" \
196 -H "Content-Type: application/json" \
197 -d '{"api":"parallel","path":"/v1beta/extract","body":{"urls":["https://example.com/article"]}}'
198```
199 
200### Create Task Run
201Initiates a task run.Returns immediately with a run object in status ‘queued’.Beta features can be enabled by setting the ‘parallel-beta’ header.
202 
203Parameters:
204- processor* (string) - Task run input with additional beta fields.
205- input* (string) - Input to the task, either text or a JSON object.
206- metadata (object) - User-provided metadata stored with the run. Keys and values must be strings with a maximum length of 16 and 512 characters respectively.
207- source_policy (object) - Optional source policy governing preferred and disallowed domains in web search results.
208- task_spec (object) - Task specification. If unspecified, defaults to auto output schema.
209- mcp_servers (object[]) - Optional list of MCP servers to use for the run.To enable this feature in your requests, specify mcp-server-2025-07-17 as one of the values in parallel-beta header (for API calls) or betas param (for the SDKs).
210- enable_events (boolean) - Controls tracking of task run execution progress. When set to true, progress events are recorded and can be accessed via the Task Run events endpoint. When false, no progress events are tracked. Note that progress tracking cannot be enabled after a run has been created. The flag is set to true by default for premium processors (pro and above).To enable this feature in your requests, specify events-sse-2025-07-24 as one of the values in parallel-beta header (for API calls) or betas param (for the SDKs).
211- webhook (object) - Callback URL (webhook endpoint) that will receive an HTTP POST when the run completes.This feature is not available via the Python SDK. To enable this feature in your API requests, specify the parallel-beta header with webhook-2025-08-12 value.
212 
213```bash
214curl -s -X POST $GOOSEWORKS_API_BASE/v1/proxy/orthogonal/run \
215 -H "Authorization: Bearer $GOOSEWORKS_API_KEY" \
216 -H "Content-Type: application/json" \
217 -d '{"api":"parallel","path":"/v1/tasks/runs"}'
218 "processor": "base",
219 "input": "Research the competitive landscape of AI coding assistants"
220}'
221```
222 
223## Use Cases
224 
2251. **Research Automation**: Get comprehensive research on any topic
2262. **OpenAI Drop-in**: Use with existing OpenAI SDK code
2273. **Competitive Analysis**: Research competitors and market
2284. **Due Diligence**: Gather information for investment decisions
229 
230## Discover More
231 
232For full endpoint details and parameters:
233 
234```bash
235curl -s -X POST $GOOSEWORKS_API_BASE/v1/proxy/orthogonal/search \
236 -H "Authorization: Bearer $GOOSEWORKS_API_KEY" \
237 -H "Content-Type: application/json" \
238 -d '{"prompt":"parallel API endpoints"}' List all endpoints
239curl -s -X POST $GOOSEWORKS_API_BASE/v1/proxy/orthogonal/details \
240 -H "Authorization: Bearer $GOOSEWORKS_API_KEY" \
241 -H "Content-Type: application/json" \
242 -d '{"api":"parallel","path":"/v1beta/findall"}' # Get endpoint details
243```
244 

Discussion

Alternatives

Also in Services & APIs
Context7Pulls up-to-date, version-specific library docs and code examples into the prompt so the AI stops inventing old APIs.Coding · MITAdaptyv Bio Foundry APIHow to use the Adaptyv Bio Foundry API and Python SDK for protein experiment design, submission, and results retrieval. Use this skill whenever the user mentions Adaptyv, Foundry API, protein binding assays, protein screening experiments, BLI/SPR assays, thermostability assays, or wants to submit protein sequences for experimental characterization. Also trigger when code imports `adaptyv`, `adaptyv_sdk`, or `FoundryClient`, or references `foundry-api-public.adaptyvbio.com`.Science · MIT.NET Backend Development PatternsMaster C#/.NET backend development patterns for building robust APIs, MCP servers, and enterprise applications. Covers async/await, dependency injection, Entity Framework Core, Dapper, configuration, caching, and testing with xUnit. Use when developing .NET backends, reviewing C# code, or designing API architectures.Coding · MITAdd AI protectionProtect AI chat and completion endpoints from abuse — detect prompt injection and jailbreak attempts, block PII and sensitive info from leaking in responses, and enforce token budget rate limits to control costs. Use this skill when the user is building or securing any endpoint that processes user prompts with an LLM, even if they describe it as "preventing jailbreaks," "stopping prompt attacks," "blocking sensitive data," or "controlling AI API costs" rather than naming specific protections.Coding · CC0-1.0